Preface ......................................................... v
Chapter 1. Survey of Early Warning Systems for Environmental
and Public Health Applications ...................... 1
1. Introduction ............................................ 1
2. Disease Surveillance .................................... 3
3. Reference Architecture for Model Extraction ............. 5
4. Problem Domain .......................................... 9
5. Data Sources ........................................... 10
6. Detection Methods ...................................... 12
7. Summary and Conclusion ................................. 13
References ................................................. 14
Chapter 2. Time-Lapse Cell Cycle Quantitative Data Analysis
Using Gaussian Mixture Models ...................... 17
1. Introduction ........................................... 18
2. Material and Feature Extraction ........................ 20
2.1. Material and cell feature extraction ............. 20
2.2. Model the time-lapse data using AR model ......... 23
3. Problem Statement and Formulation ...................... 24
4. Classification Methods ................................. 26
4.1. Gaussian mixture models and the EM algorithm ..... 26
4.2. K-Nearest Neighbor (KNN) classifier .............. 28
4.3. Neural networks .................................. 28
4.4. Decision tree .................................... 29
4.5. Fisher clustering ................................ 30
5. Experimental Results ................................... 30
5.1. Trace identification ............................. 31
5.2. Cell morphologic similarity analysis ............. 33
5.3. Phase identification ............................. 35
5.4. Cluster analysis of time-lapse data .............. 37
6. Conclusion ............................................. 40
Appendix A ................................................. 41
Appendix В ................................................. 42
References ................................................. 43
Chapter 3. Diversity and Accuracy of Data Mining Ensemble ..... 47
1. Introduction ........................................... 47
2. Ensemble and Diversity ................................. 49
2.1. Why needs diversity? ............................. 49
2.2. Diversity measures ............................... 51
3. Probability Analysis ................................... 52
4. Coincident Failure Diversity ........................... 52
5. Ensemble Accuracy ...................................... 55
5.1. Relationship between random guess and accuracy
of lower bound single models ..................... 55
5.2. Relationship between accuracy A and the number
of models N ...................................... 56
5.3. When model's accuracy < 50% ...................... 57
6. Construction of Effective Ensembles .................... 58
6.1. Strategies for increasing diversity .............. 59
6.2. Ensembles of neural networks ..................... 60
6.3. Ensembles of decision trees ...................... 61
6.4. Hybrid ensembles ................................. 62
7. An Application: Osteoporosis Classification Problem .... 62
7.1. Osteoporosis problem ............................. 63
7.2. Results from the ensembles of neural nets ........ 63
7.3. Results from ensembles of the decision trees ..... 66
7.4. Results of hybrid ensembles ...................... 67
8. Discussion and Conclusions ............................. 68
References ................................................. 70
Chapter 4. Integrated Clustering for Microarray Data .......... 73
1. Introduction ........................................... 73
2. Related Work ........................................... 77
3. Data Preprocessing ..................................... 81
4. Integrated Clustering .................................. 83
4.1. Clustering algorithms ............................ 83
4.2. Integration methodology .......................... 88
5. Experimental Evaluation ................................ 89
5.1. Evaluation methodology ........................... 89
5.2. Results .......................................... 91
5.3. Discussion ....................................... 93
6. Conclusions ............................................ 94
References ................................................. 94
Chapter 5. Complexity and Synchronization of EEG with
Parametric Modeling ................................ 99
1. Introduction .......................................... 100
1.1. Brief review of EEG recording analysis .......... 100
1.2. AR modeling based EEG analysis .................. 101
2. TV AR Modeling ........................................ 104
3. Complexity Measure .................................... 105
4. Synchronization Measure ............................... 109
5. Conclusions ........................................... 113
References ................................................ 114
Chapter 6. Bayesian Fusion of Syndromic Surveillance with
Sensor Data for Disease Outbreak Classification ... 119
1. Introduction .......................................... 120
2. Approach .............................................. 122
2.1. Bayesian belief networks ........................ 122
2.2. Syndromic data .................................. 126
2.3. Environmental data .............................. 128
2.4. Test scenarios .................................. 130
2.5. Evaluation metrics .............................. 130
3. Results ............................................... 131
3.1. Scenario 1 ...................................... 131
3.2. Scenario 2 ...................................... 134
3.3. Promptness ...................................... 135
4. Summary and Conclusions ............................... 136
References ................................................ 137
Chapter 7. An Evaluation of Over-the-Counter Medication
Sales for Syndromic Surveillance .................. 143
1. Introduction .......................................... 143
2. Background and Related Work ........................... 144
3. Data .................................................. 144
4. Approaches ............................................ 145
4.1. Lead-lag correlation analysis ................... 145
4.2. Regression test of predictive ability ........... 146
4.3. Detection-based approaches ...................... 148
4.4. Supervised algorithm for outbreak detection
in OTC data ..................................... 148
4.5. Modified Holt-Winters forecaster ................ 150
4.6. Forecasting based on multi-channel regression ... 151
5. Experiments ........................................... 153
5.1. Lead-lag correlation analysis of OTC data ....... 153
5.2. Regression test of the predicative value
of OTC .......................................... 154
5.3. Results from detection-based approaches ......... 156
6. Conclusions and Future Work ........................... 158
References ................................................ 159
Chapter 8. Collaborative Health Sentinel ..................... 163
1. Introduction .......................................... 163
2. Infectious Disease and Existing Health Surveillance
Programs .............................................. 166
3. Elements of the Collaborative Health Sentinel (CHS)
System ................................................ 170
3.1. Sampling ........................................ 170
3.2. Creating a national health map .................. 177
3.3. Detection ....................................... 177
3.4. Reaction ........................................ 183
3.5. Cost considerations ............................. 184
4. Interaction with the Health Information Technology
(HCIT) World .......................................... 185
5. Conclusion ............................................ 188
References ................................................ 189
Appendix A - HL7 .......................................... 192
Chapter 9. A Multi-Modal System Approach for Drug Abuse
Research and Treatment Evaluation: Information
Systems Needs and Challenges ...................... 195
1. Introduction .......................................... 195
2. Context ............................................... 198
2.1. Data sources .................................... 198
2.2. Examples of relevant questions .................. 199
3. Possible System Structure ............................. 201
4. Challenges in System Development and Implementation ... 204
4.1. Ontology development ............................ 204
4.2. Data source control, proprietary issues ......... 205
4.3. Privacy, security issues ........................ 205
4.4. Costs to implement/maintain system .............. 206
4.5. Historical hypothesis-testing paradigm .......... 206
4.6. Utility, usability, credibility of such
a system ........................................ 206
4.7. Funding of system development ................... 207
5. Summary ............................................... 207
References ................................................ 208
Chapter 10. Knowledge Representation for Versatile Hybrid
Intelligent Processing Applied in Predictive
Toxicology ........................................ 213
1. Introduction .......................................... 214
2. Hybrid Intelligent Techniques for Predictive
Toxicology Knowledge Representation ................... 217
3. XML Schemas for Knowledge Representation and
Processing in AI and Predictive Toxicology ............ 218
4. Towards a Standard for Chemical Data Representation
in Predictive Toxicology .............................. 220
5. Hybrid Intelligent Systems for Knowledge
Representation in Predictive Toxicology ............... 225
5.1. A formal description of implicit and explicit
knowledge-based intelligent systems ............. 226
5.2. An XML schema for hybrid intelligent systems .... 228
6. A Case Study .......................................... 231
6.1. Materials and methods ........................... 232
6.2. Results ......................................... 233
7. Conclusions ............................................ 235
References ................................................ 236
Chapter 11. Ensemble Classification System Implementation
for Biomedical Microarray Data .................... 239
1. Introduction .......................................... 240
2. Background ............................................ 241
2.1. Reasons for ensemble ............................ 241
2.2. Diversity and ensemble .......................... 241
2.3. Relationship between measures of diversity and
combination method .............................. 243
2.4. Measures of diversity ........................... 243
2.5. Microarray data ................................. 244
3. Ensemble Classification System (ECS) Design ........... 245
3.1. ECS overview .................................... 245
3.2. Feature subset selection ........................ 247
3.3. Base classifiers ................................ 248
3.4. Combination strategy ............................ 249
4. Experiments ........................................... 250
4.1. Experimental datasets ........................... 250
4.2. Experimental results ............................ 252
5. Conclusion and Further Work ........................... 254
References ................................................ 255
Chapter 12. An Automated Method for Cell Phase
Identification in High Throughput
Time-Lapse Screens ................................ 257
1. Introduction .......................................... 258
2. Nuclei Segmentation and Tracking ...................... 259
3. Cell Phase Identification ............................. 260
3.1. Feature calculation ............................. 260
3.2. Identifying cell phase .......................... 262
3.3. Correcting cell phase identification errors ..... 265
4. Experimental Results .................................. 266
5. Conclusion ............................................ 272
References ................................................ 272
Chapter 13. Inference of Transcriptional Regulatory
Networks Based on Cancer Microarray Data .......... 275
1. Introduction .......................................... 275
2. Subnetworks and Transcriptional Regulatory Networks
Inference ............................................. 277
2.1. Inferring subnetworks using z-score ............. 277
2.2. Inferring subnetworks based on graph theory ..... 278
2.3. Inferring subnetworks based on Bayesian
networks ........................................ 279
2.4. Inferring transcriptional regulatory networks
based on integrated expression and sequence
data ............................................ 283
3. Multinomial Probit Regression with Baysian Gene
Selection ............................................. 284
3.1. Problem formulation ............................. 284
3.2. Bayesian variable selection ..................... 286
3.3. Bayesian estimation using the strongest genes ... 288
3.4. Experimental results ............................ 289
4. Network Construction Based on Clustering and
Predictor Design ...................................... 293
4.1. Predictor construction using reversible jump
MCMC annealing .................................. 293
4.2. CoD for predictors .............................. 295
4.3. Experimental results on a Myeloid line .......... 296
5. Concluding Remarks .................................... 298
References ................................................ 299
Chapter 14. Data Mining in Biomedicine ........................ 305
1. Introduction .......................................... 305
2. Predictive Model Construction ......................... 306
2.1. Derivation of unsupervised models ............... 307
2.2. Derivation of supervised models ................. 311
3. Validation ............................................ 316
4. Impact Analysis ....................................... 318
5. Summary ............................................... 319
References ................................................ 319
Chapter 15. Mining Multilevel Association Rules from Gene
Ontology and Microarray Data ...................... 321
1. Introduction .......................................... 321
2. Proposed Methods ...................................... 323
2.1. Preprocessing ................................... 323
2.2. Hierarchy-information encoding .................. 324
3. The MAGO Algorithm .................................... 326
3.1. MAGO algorithm .................................. 327
3.2. CMAGO (Constrained Multilevel Association
rules with Gene Ontology) ....................... 329
4. Experimental Results .................................. 330
4.1. The characteristic of the dataset ............... 331
4.2. Experimental results ............................ 331
4.3. Interpretation .................................. 334
5. Concluding Remarks .................................... 335
References ................................................ 336
Chapter 16. A Proposed Sensor-Configuration and Sensitivity
Analysis of Parameters with Applications to
Biosensors ........................................ 339
1. Introduction .......................................... 340
2. Sensor-System Configuration ........................... 342
3. Optical Biosensors .................................... 346
3.1. Relationship between parameters ................. 347
3.2. Modelling of parameters ......................... 351
4. Discussion ............................................ 356
5. Conclusion ............................................ 358
References ................................................ 359
Epilogue ...................................................... 361
References ................................................ 364
Index ......................................................... 365
|
