International Journal of Intelligent Systems Technologies and Applications (10 papers in press)

• The Design of H∞ control methodology for Nonlinear Systems to Guarantee the Tracking Behavior in the Sense of Input-Output Spheres
  by Shun-Min Wang 
  Abstract: A general nonlinear system usually contains some uncertainties, such as plant parameter variations and uncertain inputs, which may make desired system performance hard to be achieved or even cause the closed loop system unstable. Uncertain inputs of a system usually give uncertain outputs although these inputs and outputs may be bounded in some prescribed neighborhoods, yet these uncertainties may cause a complex problem in declaring the input-output neighborhoods and may therefore make the system even harder to satisfy the prescribed performance. An H∞ control design methodology based on the tracking behavior in the sense of input-output spheres is proposed in this study to ensure that the system output is bounded in the desired output sphere while an uncertain input, which is described in an input sphere, is applied to the system. The loop-shaping technique is applied in the proposed design procedure to guarantee the system robustness against disturbances and uncertainties. To attest the feasibility of the proposed methodology, a nonlinear inverted pendulum is then studied. The computer simulation results reveal that the proposed methodology can achieve the desired performance with good tracking behavior in the sense of input-output spheres by effectively rejecting the disturbances and uncertainties of this system.
  Keywords: H∞ ; Nonlinear; Spheres; Loop-shaping
   
• Identification of Crack Location and Intensity in a Cracked Beam by Fuzzy Reasoning
  by Harish Das, Dayal Parhi 
  Abstract: In this paper a soft-computing-fuzzy-logic approach for crack identification in cantilever beam has been considered. The fuzzy controller consists of six input parameters and two output parameters. The input parameters are first three relative natural frequencies and first three relative mode shape differences in dimensionless forms. The output parameters are relative crack location and relative crack depth. Theoretical analyses have been done including the effects of crack depths and crack locations on natural frequencies and mode shapes. Several fuzzy rules are outlined for the fuzzy controller. Gaussian member ship functions are used for the fuzzy controller. The local stiffnesses at crack location of the beam have been calculated using strain energy release rate. The fuzzy rules are used to identify the location and depth of the crack. Finally the effectiveness of the developed fuzzy controller has been verified by results obtained from the developed experimental setup.
  Keywords: beam, vibration, crack, natural frequency, strain energy, mode shape, fuzzy gaussian controller
   
• NURBS-based Minimum Cost Trajectory Planning for Autonomous Robots
  by Saravanan R, ramabalan sundaresan, BALAMURUGAN, C., Sriram P 
  Abstract: This paper proposes a new novel trajectory planning method by using two evolutionary algorithms namely Elitist Non-dominated Sorting Genetic Algorithm (NSGA-II) and Differential Evolution (DE) for an autonomous robot manipulator (STANFORD robot) whose workspace includes several obstacles. The aim of the problem is to minimize a multicriterion cost function with actuator constraints, joint limits and obstacle avoidance constraints by considering dynamic equations of motion. Trajectories are defined by Non Uniform Rational B-Spline (NURBS) functions. This is a non-linear constrained optimization problem with 6 objective functions, 32 constraints and 288 variables. The multicriterion cost function is a weighted balance of transfer time, mechanical energy of the actuators, singularity avoidance, penalty function to guarantee the collision free motion, joint jerks and joint accelerations. All types of obstacles (fixed, moving and oscillating obstacles) are present in the workspace of the robot. The numerical example presented here shows the efficiency of the proposed method. The results obtained from NSGA-II and DE are compared and analyzed.
  Keywords: Optimal trajectory planning, NURBS, obstacle avoidance, moving obstacles, Evolutionary algorithms- Elitist Non-dominated Sorting Genetic Algorithm (NSGA-II), Differential Evolution (DE).
   
• Robustness Evaluation of Wavelet based Features for Continuous Speech Recognition
  by Omar Farooq, Sekharjit Datta 
  Abstract: This paper evaluates robustness of admissible wavelet packet based features for continuous speech recognition. The recognition accuracy is compared with the standard Mel Frequency Cepstral Coefficients (MFCC) under clean and noisy environment. This is carried out by adding white Gaussian noise to the phonemes of the TIMIT database to generate different levels of Signal to Noise Ratio (SNR). Further, a wavelet based denoising technique is proposed as a front end for noise reduction. Soft and hard thresholding techniques are used with one-level and two-level wavelet based denoising. The speech recogniser with Continuous Density Hidden Markov's Model (CD-HMM) is used to model the phonemes for the word recognition task. The recognition performance achieved with denoising of the input speech shows improvement as compared to without denoising of both the MFCC and the wavelet based features.
  Keywords: Automatic Speech Recognition; Feature Extraction; Hidden Markov Model; Wavelet Denoising; Wavelet Transform
   
• Personalized Distributed Information Retrieval Based Agents
  by KECHID Samir, DRIAS Habiba 
  Abstract: This paper proposes a new approach using a multi agents system for personalizing information retrieval in distributed environment. Most prior research in distributed information access focused on selecting and merging information that has the most relevant content according to the query but ignored the user’s specific needs. The underlying idea is that different users have different backgrounds, goals and interests when seeking information and thus, the same query may cover different specific information needs according to who emitted it. However, with the ever expanding Web, users are faced with a huge number of information resources. Our approach extends the state of the art in a Web-based information retrieval system in distributed environment. First, it develops models for representing both user and information source using feature based profiles. Second, it develops an agent called user-agent for managing the user profile. Third, it develops an agent called source-agent for each information source in order to manage its information source in parallel. Fourth, it develops an agent called agent-broker for cooperating between user-agent and each source-agent in order to select the best source and merge their best documents in response to the user’s query. The approach has been experimented with several known information sources. The experimental results obtained show that the approach: (1) Improve the relevance of the result. (2) Reduce the response times. (3) Improve the system extensibility.
  Keywords: distributed information retrieval, user profile, source profile, query expansion, source selection, result merging and multi-agent system
   
• Hybrid adaptive neural control for flexible manipulators
  by Amin Riad MAOUCHE, Mokhtar ATTARI 
  Abstract: This article describes a hybrid control strategy to deal with the problem of controlling flexible link manipulators. The motion control of a planar manipulator with two flexible arms is studied. Dynamics is developed in Lagrange’s formulation. A novel control system structure is proposed to control the joint position and velocity as well as the deflection of the tip for each arm. First, a non-linear control law based on the dynamic motion equation of the robot is presented and the stability analysis is studied. Then, an adaptive neural controller is implemented to compensate errors due to structured and unstructured uncertainties. Efficiency of the new controller obtained by combining the two control laws is tested facing an important variation of the dynamic parameters of the flexible manipulator and compared to the non-linear control taken solely. Simulation results show the effectiveness of the controlstrategy proposed.
  Keywords: adaptive neural network; flexible manipulator; intelligent systems; non-linear control; non-linear dynamics.
   
• Non-invasive Monitoring of Temperature Distribution inside Materials with Ultrasound Inversion Method
  by Ikuo Ihara, Manabu Takahashi 
  Abstract: A novel ultrasound inversion method for monitoring the temperature distribution inside materials being heated is presented. The method consists of an ultrasonic pulse-echo measurement and a finite difference calculation for determining a one-dimensional temperature distribution. At first, the inversion method has been applied to a numerical model of a heated plate having a temperature gradient to verify the validity of the method. To demonstrate the practicability of the method, a steel plate of 30 mm thickness being heated by contacting with 700 oC molten aluminium is evaluated. Ultrasonic pulse-echo measurements are performed for the steel during heating and the inversion method is used to determine the temperature distribution inside the steel. The internal temperature distributions determined by the ultrasound inversion almost agree with those measured using thermocouples installed in the steel.
  Keywords: non-invasive monitoring, temperature distribution, ultrasound, heated steel, inverse analysis, ultrasonic pulse echo measurement
   
• Indirect Sliding mode Neural-Network Control For Holonomic Constrained robot manipulators
  by emna zouari, Hanene Medhaffar, Nabil Debel 
  Abstract: This paper presents an adaptive neural network sliding mode control for the motion and force control of constrained robot manipulators. Radial Basis Function (RBF) neural networks are used as estimators to approximate the uncertainties in the problem formulation. Adaptive learning algorithms in neural network sliding mode control (NNSMC) are derived from the Lyapunov stability analysis, so that the stability of the proposed control scheme is proved. Simulations are performed to demonstrate the effectiveness of the proposed controller.
  Keywords: constrained manipulator; sliding mode control; Neural Network estimation; adaptive control.
   
• Enhancing Large Image Database Indexing and Retrieval Performance through Integrating Database Structure with Image Features
  by Mohammad Al-Jarrah, Faruq Al-Omari 
  Abstract: In this paper, a two-dimensional hash table structure based on image discriminator measure is proposed to design an image database indexing and retrieval system. Unlike many other techniques such as R-tree, FastMap, MetricMap, and SparseMap where a false query result could happen, the results of a query of our proposed system can retrieve exactly same results as if we using full search for the query image in the image database. Hence more, the designed system outperforms existing systems that are based on sequential search, OMNI-family, and R-tree structures in terms of number of operations and precision.
  Keywords: Image Indexing and Retrieval; Image Database; Hash Tables; Similarity Retrieval; Content-Based Retrieval
   
• A Vision based Approach for Intelligent Robot Navigation
  by Genci Capi 
  Abstract: In this paper, we present an evolutionary approach for vision based robot navigation in human environments. In our method, we convert the captured image in a binary one, which after the partition is used as the input of the neural controller. The neural control system, which maps the visual information to motor commands, is evolved online using real robots. We show that evolved neural networks performed well in indoor human environments. Furthermore, we compare the performance of neural controllers with an algorithmic vision based control method.
  Keywords: robot navigation, vision, neural networks, evolutionary algorithm.