By Topic

Electronics, Robotics and Automotive Mechanics Conference (CERMA), 2011 IEEE

Date 15-18 Nov. 2011

Filter Results

Displaying Results 1 - 25 of 89
  • [Front cover]

    Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (551 KB)  
    Freely Available from IEEE
  • [Title page i]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (64 KB)  
    Freely Available from IEEE
  • [Title page iii]

    Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (111 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (120 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): v - xi
    Save to Project icon | Request Permissions | PDF file iconPDF (145 KB)  
    Freely Available from IEEE
  • Message from General Chair

    Page(s): xii
    Save to Project icon | Request Permissions | PDF file iconPDF (31 KB)  
    Freely Available from IEEE
  • Organizing Committee

    Page(s): xiii - xiv
    Save to Project icon | Request Permissions | PDF file iconPDF (32 KB)  
    Freely Available from IEEE
  • Reviewers

    Page(s): xv - xvi
    Save to Project icon | Request Permissions | PDF file iconPDF (107 KB)  
    Freely Available from IEEE
  • Computing Resonance Frequency Curves in Parametrically Switched RLC Circuit with Application to Analog Filtering

    Page(s): 3 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (305 KB) |  | HTML iconHTML  

    In this paper the parametric resonance is exploited for analog filtering applications, a RLC circuit is parametrically excited by a two-potential periodic function thus a monodromy matrix approach is used to compute the resonance frequency curves which separated the plane amplitude-frequency in stable and unstable domains then a novel scheme shows how a band pass filter is implemented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sine Wave Oscillator Using a Mathematical Function

    Page(s): 8 - 13
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (982 KB) |  | HTML iconHTML  

    This paper proposes an alternative sine wave oscillator using as a point of departure a mathematical function based on the characteristics of sinusoids. This solution has some advantages on phase-shift oscillator of three and two RC sections. Preliminary experimental results showed us that the problem of warm-up on low-frequency oscillator should be fixed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling of a CMOS Active Pixel Image Sensor: Towards Sensor Integration with Microfluidic Devices

    Page(s): 14 - 19
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (219 KB) |  | HTML iconHTML  

    Recently, micro fluidic devices have received considerable attention because of the many potential applications in medicine and environmental monitoring. In such systems, cells and particles suspended in fluids can be manipulated for analysis. Micro fluidic systems are projected to develop more complex functions as they integrate electronic/optoelectronic sensors that could monitor the activity within micro channels. This paper presents research work on modeling and simulation of a CMOS Active Pixel Sensor providing some basis for the future integration with micro fluidic devices. Computer simulations are carried out demonstrating the functionality of each stage of the sensor and a small pixel array is modeled and simulated incorporating the addressing and reset signals. Results illustrate how the performance of the CMOS active pixel sensor can be adjusted to meet the specifications for scientific applications. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Multi-channel Sinusoidal Generator for Electrokinetic Stimulation of Microfluidic Platforms

    Page(s): 20 - 25
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1969 KB) |  | HTML iconHTML  

    This paper presents a multi-channel sinusoidal generator based in triangle-to-sine (TSC) converters. The proposed signal generator is used as stimulator of electro kinetic micro fluidic platforms for particle manipulation. The device is capable to deliver sixteen independent sinusoidal signals with control of amplitude and frequency. The multi-generator presents a frequency range of 8kHz to 21MHz with an output range of 0V to 3.1VPP. The output voltage can be extended to give outputs with amplitudes up to 20VPP using an interface card. The proposed multi-oscillator is based in an application specific circuit, was fabricated in a 0.35um CMOS technology and has a footprint area of 1560um × 2030um. The multi-channel sinusoidal generator was tested using an experimental set-up where the separation of live and dead cells was performed. The experimental set-up consisted of a micro fluidic platform with a Carbon DEP micro-channel with 3-dimensional carbon electrodes. Simulations were carried out to reproduce the effects of electro kinetic forces over cells. By choosing specific frequencies, live and dead cells were trapped to one side (port), while only dead cells were attracted to the other port of the micro-channel. This stimulation device can be used in many other electro kinetic tasks to perform characterization, trapping and separation of particles. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Artificial Organic Networks

    Page(s): 29 - 34
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (877 KB) |  | HTML iconHTML  

    This paper introduces a novel artificial intelligence technique bio-inspired on organic chemistry: Artificial Organic Networks (AON). In fact, organic compounds present several characteristics as stability, well-formed molecules, and easily-spanning. Thus, these compounds can be taken as inspiration in which a primitive structure assures stability in itself, and then some of these structures might be mixed in order to form more complex structures in a natural and easy way, also assuring stability. In this context, there exists the opportunity to investigate and to create new organic structures, not only based on primary elements. Thus, organic chemistry knowledge and mathematical formalization are applied into this new algorithm. Moreover, Artificial Hydrocarbon Networks (AHN), particular artificial organic compounds, are also defined and implemented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Genetically Enhanced Intelligent Speed Control for Induction Machines Using Direct Torque Control

    Page(s): 35 - 40
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (446 KB) |  | HTML iconHTML  

    This paper presents a novel fuzzy controller that controls speed on induction machines using direct torque control. DTC is used to facilitate the control of the induction machine. Speed control is based in non-interactive PID control theory and Mamdani fuzzy systems. Genetic algorithm techniques are used for offline optimizations of the normalization factors (they dictate what portion of the decision table is used) and limits of membership functions. Simulations are presented, results and conclusions are discussed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Outlier Detection Applying an Innovative User Transaction Modeling with Automatic Explanation

    Page(s): 41 - 46
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (237 KB) |  | HTML iconHTML  

    We present a method to detect outlier or exceptional transactions records applying an innovative user modeling. We use a large financial database to validate our method. Our method has two stages. The first stage is for user transaction modeling and it obtains user behavior according to historic transactions based on categorical or numerical attributes. The second stage is the monitoring where a new transaction is compared against the corresponding user model, in order to determine if this transaction is unusual (no standard, fraudulent or suspicious). The novelty of this method is that it provides to the user with an automatic explanation about the exception level of the new transaction (e.g. transaction normal, abnormal, suspicious, etc.). And also provides the percentage of ownership to them. According to the experiments conducted with a very large financial database, encouraging results were observed in the field of applied Business Intelligence, in particular to the financial frauds detection and in general to the outlier detection area. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On-Line Production Cost Optimization in High Performance Machining Operations through AI Techniques

    Page(s): 47 - 52
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (540 KB) |  | HTML iconHTML  

    This paper proposes an on-line adaptive control with optimization (ACO) system for optimizing the production cost subjected to quality constraints in high performance machining operations of hardened steel. Unlike traditional approaches for optimizing production cost, this paper deals with optimizing the cutting operation considering the real state of the cutting-tool. Artificial intelligence techniques for modeling (Artificial Neural Networks) and optimizing (Genetic Algorithms and Mesh Adaptive Direct Search algorithms) are applied for this purpose. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Input-Output Stability for Differential Neural Networks

    Page(s): 53 - 58
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (254 KB) |  | HTML iconHTML  

    This paper deals with the problem to obtain input-output stability for a certain class of differential neural networks. Hence, by using a Lyapunov function, the conditions to guarantee finite-gain L-stability, which also ensures global exponential stability (GES), are established. Finally, the simulation of a numerical example illustrates the applicability of this approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experimental Fatigue Crack Propagation Simulation by ANN of a Newly Developed Controlled Rolled Microalloyed Steel Plate

    Page(s): 59 - 64
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1027 KB) |  | HTML iconHTML  

    In this work, fatigue crack propagation life of a new micro alloyed steel plate under the influence of constant load ratio was simulated by using artificial neural network (ANN). Numerous methodologies such as cycle by cycle prediction, prediction by correlation and finite element methods have been proposed for simulating fatigue life [1]. However, few studies relate ANNs for modeling the fatigue crack growth propagation in materials particularly for micro alloyed steels technology. The applied ANNs simulation methodology showed great potential for simulating the experimental fatigue crack growth rate complex data set. In this case especially by interpolation within the trial tested range. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • FPGA Based LIRA Neural Classifier

    Page(s): 65 - 70
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (878 KB) |  | HTML iconHTML  

    Neural networks can be used for image classification. They are powerful instruments in image and pattern recognition because they have following advantages: parallel structure, training in the process of the classifier preparation, and possibility to implement them as an electronic circuit. A special type of neural classifier, LIRA (Limited Receptive Area) neural classifier, has been developed and used to solve different tasks, for example, handwritten digit recognition, face recognition, texture and shape recognition, etc. It is important to reduce the time of system work so the neural classifier was implemented in a FPGA device. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Chaotic Time Series Prediction with Feature Selection Evolution

    Page(s): 71 - 76
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (268 KB) |  | HTML iconHTML  

    Chaotic time series have been successfully predicted with the EPNet algorithm through the evolution of artificial neural networks. However, the input feature selection problem has either not been fully explored before or has not been compared against other algorithms in the literature. This paper presents four algorithms derived from the classical EPNet algorithm to evolve the input feature selection in three different chaotic series: Logistic, Lorenz and Mackey-Glass. Additionally, some flaws in the prediction field that may be considered in future works are discussed. A comparison against previous work demonstrates that in most cases the specialization of the EPNet algorithm allows better solutions with a smaller number of generations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Continuous-Time Neural Identification for a 2 DOF Vertical Robot Manipulator

    Page(s): 77 - 82
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (264 KB) |  | HTML iconHTML  

    A Recurrent High-Order Neural Network (RHONN) structure as well as a decentralized neural network scheme, this latter with high-order interconnections, are proposed to execute continuous-time identification of a two degrees of freedom (DOF) direct drive vertical planar robot manipulator model, on which effects due to friction and gravity forces are both considered. The neural network learning is achieved online using the filtered error approach. The performance of both neural networks schemes is illustrated via simulation results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Separation and Identification of Environmental Noise Signals Using Independent Component Analysis and Data Mining Techniques

    Page(s): 83 - 88
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (732 KB) |  | HTML iconHTML  

    In the present work, we show a way to separate noise signals recorded with microphones industrial, in order that they can be analyzed separately. Blind Source Separation is accomplished using Independent Component Analysis (ICA) technique in the wavelet domain. Also, it is necessary to identify the separate sources, taking into account that each signal separate has some components of the signals belonging to the initial mixture. Through data mining techniques and characteristic features of the signals obtained are derived rules in order to identify the main source that is present in the mix, for this we propose the use of data mining techniques. The results show a substantial improvement in the separation of mixtures of real environmental noise using ICA, although the mixtures are not fully independent. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computer Tool for Analyzing Gases in Power Transformers

    Page(s): 89 - 94
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (532 KB) |  | HTML iconHTML  

    When the insulation of a power transformer is subjected to excessive thermal or electrical stress, the links of the chemical compounds of the oil and the cellulose in the transformer can rupture and produce different gases. The analysis of the type and concentration of these compounds may represent the state of insulation of the transformer. There are three main approaches for this analysis: Analysis of gases through traditional methods, analysis of gases through the modeling of expert knowledge, and analysis of gases according to the historical evolution of the variables. This paper presents the design and development of a tool to monitor the transformers of different power stations, applying the three analysis approaches. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection of the Tiredness Level of Drivers Using Machine Vision Techniques

    Page(s): 97 - 102
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (219 KB) |  | HTML iconHTML  

    This paper presents a machine vision system to detect fatigue in drivers based on the percentage of closing eyes and detection of yawning and nodding. The system outputs are no fatigue, alarm and critical stage (fatigue). The characteristics are extracted from videos by using image processing techniques such as histogram analysis and color spaces. The decision on the tiredness level is the result of a combination of extracted characteristics. The global performance achieved in characteristic extraction is about 90% and 86% for classification, the processing time to produce a response is close to 40 ms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimizing Feature Selection Techniques for Sentiment Classification

    Page(s): 103 - 107
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (145 KB) |  | HTML iconHTML  

    A hybrid feature selection method is proposed to distinguish the salient features that allow identifying the viewpoint underlying a text review, that is, to determine its sentiment polarity. This method makes use of fundamental pre-processing tasks known as filter and wrapper techniques. The effectiveness of this approach is demonstrated on a data set where each document is represented by two distinct feature vectors based on two different sets of rules. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.