xx
Contents
Part V Classifieation of Eeologieal Images at Miero and
Maero Seale ............................................................................................... 353
18. Identification of Marine Microalgae by Neural Network
Analysis of Simple Descriptors of Flow Cytometric Pulse
Shapes .............................................................................................. 355
18. 1 Introduction ......................................................................................... 355
18.2Materials and Methods ........................................................................ 359
18.2.1 Pulse Shape Extraction ................................................................ 359
18.2.2 Data Filtering ............................................................................... 359
18.2.3 Data Transformation .................................................................... 359
18.2.4 Principal Component Analysis .................................................... 360
18.2.5 Neural Network Analysis ............................................................ 362
18.2.6 Hardware and Software .............................................................. 363
18.3Results ................................................................................................. 363
18.4 Discussion ........................................................................................... 365
18.5Conclusions ......................................................................................... 365
Acknowledgement ................................................................................. 365
References ............................................................................................. 366
19. Age Estimation of Fish Using a Probabilistic Neural
Network ............................................................................................. 369
19.1 Introduction ......................................................................................... 369
19.2Traditional Methods of Age Estimation .............................................. 369
19.3Approaches to Automation in Fish Age Estimation ............................ 371
19.4The Application of a Probabilistic Neural Network to Fish Age
Estimation .......................................................................................... 372
19 .5Results ................................................................................................. 376
19.6Discussion ........................................................................................... 378
Acknowledgements ............................................................................... 380
References ............................................................................................. 380
20. Pattern Recognition and Classification of Remotely Sensed
Images by Artificial Neural Networks ....................................... 383
20.1 Introduction ......................................................................................... 383
20.2Neural Networks in Remote Sensing .................................................. 384
20.2.1 Classification Applications .......................................................... 384
20.2.2 Regression Applications .............................................................. 385
20.3The Neural Networks Used in Remote Sensing .................................. 385
20.3.1 Feedforward Neural Networks ..................................................... 386
20.3.1.1 Multi-Layer Perceptron (MLP ..................................................... 387
20.3.1.2 Radial Basis Function (RBF ........................................................ 388
20.3.1.3 Probabilistic Neural Networks (PNN ........................................... 390
20.3.1.4 Generalised Regression Neural Networks (GRNN ...................... 390
20.3.1.5 Other Network Types .................................................................. 391
20.4Current Status ..................................................................................... 392
Contents
Part V Classifieation of Eeologieal Images at Miero and
Maero Seale ............................................................................................... 353
18. Identification of Marine Microalgae by Neural Network
Analysis of Simple Descriptors of Flow Cytometric Pulse
Shapes .............................................................................................. 355
18. 1 Introduction ......................................................................................... 355
18.2Materials and Methods ........................................................................ 359
18.2.1 Pulse Shape Extraction ................................................................ 359
18.2.2 Data Filtering ............................................................................... 359
18.2.3 Data Transformation .................................................................... 359
18.2.4 Principal Component Analysis .................................................... 360
18.2.5 Neural Network Analysis ............................................................ 362
18.2.6 Hardware and Software .............................................................. 363
18.3Results ................................................................................................. 363
18.4 Discussion ........................................................................................... 365
18.5Conclusions ......................................................................................... 365
Acknowledgement ................................................................................. 365
References ............................................................................................. 366
19. Age Estimation of Fish Using a Probabilistic Neural
Network ............................................................................................. 369
19.1 Introduction ......................................................................................... 369
19.2Traditional Methods of Age Estimation .............................................. 369
19.3Approaches to Automation in Fish Age Estimation ............................ 371
19.4The Application of a Probabilistic Neural Network to Fish Age
Estimation .......................................................................................... 372
19 .5Results ................................................................................................. 376
19.6Discussion ........................................................................................... 378
Acknowledgements ............................................................................... 380
References ............................................................................................. 380
20. Pattern Recognition and Classification of Remotely Sensed
Images by Artificial Neural Networks ....................................... 383
20.1 Introduction ......................................................................................... 383
20.2Neural Networks in Remote Sensing .................................................. 384
20.2.1 Classification Applications .......................................................... 384
20.2.2 Regression Applications .............................................................. 385
20.3The Neural Networks Used in Remote Sensing .................................. 385
20.3.1 Feedforward Neural Networks ..................................................... 386
20.3.1.1 Multi-Layer Perceptron (MLP ..................................................... 387
20.3.1.2 Radial Basis Function (RBF ........................................................ 388
20.3.1.3 Probabilistic Neural Networks (PNN ........................................... 390
20.3.1.4 Generalised Regression Neural Networks (GRNN ...................... 390
20.3.1.5 Other Network Types .................................................................. 391
20.4Current Status ..................................................................................... 392