Handbook of Data Science Approaches for Biomedical Engineering covers the research issues and concepts of biomedical engineering progress and the ways they are aligning with the latest technologies in IoT and big data. In addition, the book includes various real-time/offline medical applications that directly or indirectly rely on medical and information technology. Case studies in the field of medical science, i.e., biomedical engineering, computer science, information security, and interdisciplinary tools, along with modern tools and the technologies used are also included to enhance understanding.
Today, the role of Big Data and IoT proves that ninety percent of data currently available has been generated in the last couple of years, with rapid increases happening every day. The reason for this growth is increasing in communication through electronic devices, sensors, web logs, global positioning system (GPS) data, mobile data, IoT, etc.
1. 1. Introduction - p. 252 2. Part 1: Theory background - p. 253 3. 1.1. Image segmentation problem - p. 253 4. 1.2. Data clustering - p. 255 5. 1.3. Fuzzy clustering - p. 255 6. 1.4. Semisupervised fuzzy clustering - p. 256 7. Part 2: The combination of eSFCM and OTSU in image segmentation - p. 258 8. 2.1. The general diagram of the integration between the eSFCM and OTSU - p. 258 9. 2.2. OTSU threshold algorithm in image processing - p. 258 10. Part 3: Semisupervised fuzzy clustering with spatial feature - p. 261 11. 3.1. The general framework - p. 261 12. 3.2. Determining suitable additional information - p. 262 13. 3.3. The semisupervised fuzzy clustering algorithm (SSFC-SC) - p. 263 14. 3.4. Fuzzy satisficing method and semisupervised clustering method in segmentation problem (SSFC-FS [35]) - p. 267 15. 3.5. The properties and consequences from solution analysis - p. 271 16. 3.6. The advantages of the proposed algorithms - p. 275 17. Part 4: Defining the suitable additional information for SSFC-FS algorithm - p. 275 18. 4.1. The framework of the SSFC-FSAI method - p. 275 19. 4.2. The set of additional information functions - p. 276 20. 4.3. Defining an appropriate additional information - p. 278 21. 4.4. Advantages of the new algorithm - p. 280 22. Part 5: The results of implementations and applications - p. 282 23. 5.1. Dental X-ray image dataset - p. 282 24. 5.2. The performance among segmentation methods - p. 283 25. 2. Conclusions - p. 286 26. Index - p. 291
Handbook of Data Science Approaches for Biomedical Engineering covers the research issues and concepts of biomedical engineering progress and the ways they are aligning with the latest technologies in IoT and big data. In addition, the book includes various real-time/offline medical applications that directly or indirectly rely on medical and information technology. Case studies in the field of medical science, i.e., biomedical engineering, computer science, information security, and interdisciplinary tools, along with modern tools and the technologies used are also included to enhance understanding.
Today, the role of Big Data and IoT proves that ninety percent of data currently available has been generated in the last couple of years, with rapid increases happening every day. The reason for this growth is increasing in communication through electronic devices, sensors, web logs, global positioning system (GPS) data, mobile data, IoT, etc.
1. 1. Introduction - p. 252 2. Part 1: Theory background - p. 253 3. 1.1. Image segmentation problem - p. 253 4. 1.2. Data clustering - p. 255 5. 1.3. Fuzzy clustering - p. 255 6. 1.4. Semisupervised fuzzy clustering - p. 256 7. Part 2: The combination of eSFCM and OTSU in image segmentation - p. 258 8. 2.1. The general diagram of the integration between the eSFCM and OTSU - p. 258 9. 2.2. OTSU threshold algorithm in image processing - p. 258 10. Part 3: Semisupervised fuzzy clustering with spatial feature - p. 261 11. 3.1. The general framework - p. 261 12. 3.2. Determining suitable additional information - p. 262 13. 3.3. The semisupervised fuzzy clustering algorithm (SSFC-SC) - p. 263 14. 3.4. Fuzzy satisficing method and semisupervised clustering method in segmentation problem (SSFC-FS [35]) - p. 267 15. 3.5. The properties and consequences from solution analysis - p. 271 16. 3.6. The advantages of the proposed algorithms - p. 275 17. Part 4: Defining the suitable additional information for SSFC-FS algorithm - p. 275 18. 4.1. The framework of the SSFC-FSAI method - p. 275 19. 4.2. The set of additional information functions - p. 276 20. 4.3. Defining an appropriate additional information - p. 278 21. 4.4. Advantages of the new algorithm - p. 280 22. Part 5: The results of implementations and applications - p. 282 23. 5.1. Dental X-ray image dataset - p. 282 24. 5.2. The performance among segmentation methods - p. 283 25. 2. Conclusions - p. 286 26. Index - p. 291
