The Design And Training Of An Intelligent Sensor Implementation

• doi: 10.1109/CCECE.1993.332465
• title: The design and training of an intelligent sensor implementation
• publisher: IEEE
• isbn: 0-7803-2416-1
• issn:
• partnum: 93TH0590-0
• rank: 3796
• access_type: LOCKED
• content_type: Conferences
• abstract: The design and VLSI implementation of an intelligent sensor that can be used for process control applications requiring image capture or non-contact measurement is presented in this paper. The sensor architecture is based on an analog VLSI realization of an artificial neural network with an integrated photosensitive array. A 10/spl times/10 array of photosensitive cells has been designed as the input nodes to a two-layer feedforward neural network. Four groups each with 25 photosensors are fully connected to 4 neurons respectively in the hidden layer. The 16 hidden neurons are fully connected to 5 neurons in the output layer. A development program has been written that determines the optimal set of weights using the modified backpropagation algorithm. The neural network has been trained to recognize 18 different types of patterns. The final implementation of this intelligent sensor has the dimensions of 4500/spl times/4820 design scale microns and contains approximately 1630 analog devices fabricated using a 3/spl mu/ single-polysilicon, double-metal, p-well CMOS process.<>
• article_number: 332465
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=332465
• html_url: https://ieeexplore.ieee.org/document/332465/
• abstract_url: https://ieeexplore.ieee.org/document/332465/
• publication_title: Proceedings of Canadian Conference on Electrical and Computer Engineering
• conference_location: Vancouver, BC, Canada
• conference_dates: 14-17 Sept. 1993
• publication_number: 1086
• is_number: 7848
• publication_year: 1993
• publication_date: 14-17 Sept. 1993
• start_page: 1174
• end_page: 1177 vol.2
• citing_paper_count: 0
• citing_patent_count: 0
• download_count: 58
• insert_date: 20020806
• index_terms:
  • ieee_terms:
    • Intelligent sensors
    • Sensor arrays
    • Neurons
    • Very large scale integration
    • Artificial neural networks
    • Neural networks
    • Process control
    • Feedforward neural networks
    • Backpropagation algorithms
    • Pattern recognition
  • dynamic_index_terms:
    • Intelligent Sensors
    • Neural Network
    • Artificial Neural Network
    • Neural Network Model
    • Typical Pattern
    • Output Layer
    • Hidden Layer
    • Neurons In Layer
    • Feed-forward Network
    • Feedforward Neural Network
    • Sensor Design
    • Different Types Of Patterns
    • Non-contact Measurement
    • Photosensitive Cells
    • Activation Function
    • Learning Algorithms
    • Machine Learning Algorithms
    • Circuitry
    • Sigmoid Function
    • Sigmoidal Curve
    • S-shaped
    • Nonlinear Function
    • Nonlinear Mapping
    • Weight Matrix
    • Weight Matrices
    • Electrical Signals
    • Phototransistor
    • Sigmoid Activation Function
    • Synaptic Weights
    • Multilayer Feedforward Neural Network
    • Neuron Activation Function
    • Differential Amplifier
    • Extra Input
    • Optimal Matrix
    • Optimal Matrices
    • Digital Signal
    • Neural Function
• isbn_formats:
  • format: Print ISBN, value: 0-7803-2416-1, isbnType: Historical
  • format: Print ISBN, value: 0-7803-1443-3, isbnType: Historical
• authors:
  • Author Name: Xiangui Yu
    Affiliation: Department of Electrical Engineering, University of Windsor, Windsor, ONT, Canada
    Author URL: https://ieeexplore.ieee.org/author/37087453961
    ID: 37087453961
    Order: 1
    Author Affiliations:
    • Department of Electrical Engineering, University of Windsor, Windsor, ONT, Canada
  • Author Name: N.K. Loh
    Affiliation: Center for Robotics and Advanced Automation Dodge Hall of Engineering, Oakland University, Rochester, MI, USA
    Author URL: https://ieeexplore.ieee.org/author/37295882400
    ID: 37295882400
    Order: 2
    Author Affiliations:
    • Center for Robotics and Advanced Automation Dodge Hall of Engineering, Oakland University, Rochester, MI, USA
  • Author Name: G.A. Jullien
    Affiliation: Department of Electrical Engineering, University of Windsor, Windsor, ONT, Canada
    Author URL: https://ieeexplore.ieee.org/author/37276214100
    ID: 37276214100
    Order: 3
    Author Affiliations:
    • Department of Electrical Engineering, University of Windsor, Windsor, ONT, Canada
  • Author Name: W.C. Miller
    Affiliation: Department of Electrical Engineering, University of Windsor, Windsor, ONT, Canada
    Author URL: https://ieeexplore.ieee.org/author/37269502100
    ID: 37269502100
    Order: 4
    Author Affiliations:
    • Department of Electrical Engineering, University of Windsor, Windsor, ONT, Canada

Image Sensor

• sensor_type: CMOS
• resolution: 10x10
• dynamic_range: Not specified
• pixel_size: Not specified
• dark_current: Not specified

Optical Data

• focal_length: Not specified
• aperture: Not specified
• field_of_view: Not specified
• distortion: Not specified

Performance Metrics

Applications & Benefits

• cell_imaging: The intelligent sensor can be used for process control applications requiring image capture or non-contact measurement.
• benefits: Allows for the identification of various patterns from laser light reflected from objects.

Supporting Organizations

• supported_by: University of Windsor, Center for Robotics and Advanced Automation at Oakland University

Manuscript Details

• publication_date: 14-17 Sept. 1993

Relevancy Score

• score: 8
• missing_fields:
  • fill factor
  • quantum efficiency
  • readout speed
  • temporal noise
  • fixed-pattern noise
  • analog-to-digital conversion techniques
  • microlenses
  • on-chip colour filters
  • global or rolling shutters
  • backside illumination

Processed JSON Filename

request_107b312c-189c-4d18-a20d-425055ac0cc7-the_design_and_training_of_an_intelligent_sensor_implementation.json