Loading...
Search for:
neuro-fuzzy-network
0.007 seconds
Frontal Plane Balance Control of a Biped Robot Based on Human Balancing Strategy
, M.Sc. Thesis Sharif University of Technology ; Farahmand, Farzam (Supervisor) ; Hoviattalab, Maryam (Supervisor)
Abstract
The capability to control and maintain upright posture is a fundamental requirement for humanoid robots. Although many control algorithms were successfully presented, it seems developing a new controller inspired from human balance strategy would greatly improve performance and reduce energy consumption. To study the control strategy used by human nerves system more precisely, a balancing exercise was designed and implemented. Five human subjects were asked to stand on an unstable tilting board and balance the board. Instantaneous Eulerian angles of body segments of human subjects were captured by utilizing Xsense orientation sensors. A humanoid robot standing on the tilting board was...
Two new methods for DNA splice site prediction based on neuro-fuzzy network and clustering
, Article Neural Computing and Applications ; Volume 23, Issue SUPPL1 , 2013 , Pages 407-414 ; 09410643 (ISSN) ; Manzuri Shalmani, M. T ; Khaki Sedigh, A ; Kia, M ; Sharif University of Technology
2013
Abstract
Nowadays, genetic disorders, like cancer and birth defects, are a great threat to human life. Since the first noticing of these types of diseases, many efforts have been made and researches performed in order to recognize them and find a cure for them. These disorders affect genes and they appear as abnormal traits in a genetic organism. In order to recognize abnormal genes, we need to predict splice sites in a DNA signal; then, we can process the genetic codes between two continuous splice sites and analyze the trait that it represents. In addition to abnormal genes and their consequent disorders, we can also identify other normal human traits like physical and mental features. So the...
Modeling of a Vague Problem (Floating Breakwater by BEM Analysed) Using ANFIS (Adaptive Neuro-Fuzzy Inference System) and Validation by Fuzzy Boundary Element Method
, M.Sc. Thesis Sharif University of Technology ; Abbaspour Tehrani, Majid (Supervisor)
Abstract
The thesis title is “Modeling of a vague problem (Floating Breakwater by BEM Analysed) using ANFIS (Adaptive Neuro-Fuzzy Inference System) and validation by Fuzzy Boundary Element Method”. In this set of material, more important definitions are described below. When some input data is linguistics, or we have lack of Information or Vagueness, Fuzzy toolbox can alleviate the problem. Fuzzy concept includes several fields and applications like; fuzzy logic, fuzzy sets, fuzzy control, fuzzy arithmetic and fuzzy inference, and the last two applications are used in this thesis. The Neural network is a black box, Neurons that can justify their actions and these artificial brains can grow. The...
Neutron Noise Reconstruction Based on Neuro-Fuzzy Computing for VVER-1000 Reactor Core
, M.Sc. Thesis Sharif University of Technology ; Vosoughi, Naser (Supervisor) ; Hosseini, Abolfazl (Co-Supervisor)
Abstract
In this study, the reconstruction of the neutron noise source in the core of the VVER-1000 reactor was carried out using fuzzy neural network and parallel processing of parallel process circuit design. The noise of power reactors is derived from neutron fluctuations. Which are affected by fluctuations in reactor characteristics. These oscillations can be caused by the displacement of the elements forming the core or due to changes in temperature or density and so on. It is clear that any change in the elements of a reactor will make itself a change in the corresponding to cross-section of material. These changes called as pertubation. In this project, by using neuro-fuzzy network...
Position control of a wheel-based miniature magnetic robot using neuro-fuzzy network
, Article Robotica ; Volume 40, Issue 11 , 2022 , Pages 3895-3910 ; 02635747 (ISSN) ; Pishkenari, H. N ; Zohoor, H ; Sharif University of Technology
Cambridge University Press
2022
Abstract
Untethered small-scale robots can accomplish tasks which are not feasible by conventional macro robots. In the current research, we have designed and fabricated a miniature magnetic robot actuated by an external magnetic field. The proposed robot has two coaxial wheels and one magnetic dipole which is capable of rolling and moving on the surface by variation in the direction of magnetic field. To generate the desired magnetic field, a Helmholtz electromagnetic coil is manufactured. To steer the robot to the desired position, at first the robot dynamics is investigated, and subsequently a controller based on a neuro-fuzzy network has been designed. Finally, the proposed controller is...
The Use of Enhanced Chemometric Methods in QSAR and Pattern Recognition Studies
, Ph.D. Dissertation Sharif University of Technology ; Jalali Heravi, Mehdi (Supervisor)
Abstract
Chemometrics is an interdisciplinary subject which has many applications among science and industrial process. Environmental chemist, Food chemist, biologist and so on depend on good analytical chemistry measurement and so need chemometrics to interpret their data. In this project, we have developed different chemometrics and machine learning methods for considering the quantitative structure-activity relationship between different drug-like molecules. Also some chemometrics techniques were applied for the pattern recognition of NIR data on human plasma for discriminating between healthy and infected HIV-1 patients. At first, Quantitative structure-activity relationship (QSAR) models for...
A novel method for modeling the magnetizing yoke
, Article Electromagnetics ; Volume 30, Issue 3 , 2010 , Pages 297-308 ; 02726343 (ISSN) ; Norouzi, E
2010
Abstract
Magnetic flux leakage is the most widely used method for oil and gas pipeline non destructive testing. The saturation level of the sample under test has a significant effect on its efficiency; therefore, the magnetizing yoke requires an elaborate design. The finite element method is the conventional approach used for this purpose, but it is very time consuming. In this article, a neuro-fuzzy method is presented to model the behavior of the magnetizing yoke. Modeling a few different designs with the finite element method and using the results for training the neuro-fuzzy model eradicates the necessity of modeling a huge number of designs with the finite element method. The acquired...