Artificial Intelligence in Data Mining: Theories and Applications

✍ Scribed by D. Binu (editor), B.R. Rajakumar (editor)

• Publisher: Academic Press
• Year: 2021
• Tongue: English
• Leaves: 271
• Category: Library

✦ Synopsis

Artificial Intelligence in Data Mining: Theories and Applications offers a comprehensive introduction to data mining theories, relevant AI techniques, and their many real-world applications. This book is written by experienced engineers for engineers, biomedical engineers, and researchers in neural networks, as well as computer scientists with an interest in the area.

✦ Table of Contents

Front Cover
Artificial Intelligence in Data Mining
Copyright Page
Contents
List of contributors
Preface
1 Introduction
1.1 Data mining
1.2 Description of data mining
1.2.1 Different databases adapted for data mining
1.2.2 Different steps in design process for mining data
1.3 Tools in data mining
1.4 Data mining terminologies
1.5 Merits of data mining
1.6 Disadvantages of data mining
1.7 Process of data mining
1.8 Data mining techniques
1.9 Data mining applications
1.10 Intelligent techniques of data mining
1.11 Expectations of data mining
References
2 Intelligence methods for data mining task
2.1 Introduction
2.2 Procedure for intelligent data mining
2.2.1 Interest-driven data mining
2.2.2 Data-driven data mining
2.3 Associate rule mining
2.3.1 Different kinds of association rules
2.4 Association rule mining: multiobjective optimization method
2.5 Intelligent methods for associate rule mining
2.5.1 Associate rule mining based on the optimization method
2.6 Associate rule mining using genetic algorithm
2.7 Association rule mining using particle swarm optimization
2.8 Bees swarm optimization–association rule mining algorithm
2.9 Ant colony optimization algorithm
2.10 Penguins search optimization algorithm for association rules mining Pe-ARM
2.11 Deep learning in data mining
References
3 Unsupervised learning methods for data clustering
3.1 Data clustering
3.1.1 Why clustering?
3.1.2 Fundamentals of cluster analysis
3.1.3 Needs of unsupervised learning: Why?
3.1.4 Partitional clustering
3.2 Mode seeking and mixture-resolving algorithms
3.2.1 Gaussian mixture models
3.2.2 Hierarchical clustering
3.2.3 Hierarchical divisive algorithms
3.3 Conclusion
4 Heuristic methods for data clustering
4.1 What is the heuristic method?
4.1.1 Heuristic method and the formulation of exact solutions
4.1.2 Clustering-based heuristic methodologies
4.2 Summary
5 Deep learning methods for data classification
5.1 Data classification
5.2 Data mining
5.2.1 Steps involved in data mining process
5.3 Background and evolution of deep learning
5.4 Deep learning methods
5.4.1 Fully connected neural network
5.4.2 Deep neural network
5.4.3 Deep convolutional neural network
5.4.4 Deep recurrent neural network
5.4.5 Deep generative adversarial network
5.4.6 Deep reinforcement learning
5.4.7 Deep recursive neural network
5.4.8 Deep long–short-term memory
5.4.9 Hierarchical deep learning for text
5.4.10 Deep autoencoder
5.4.11 Random multimodel deep learning
References
6 Neural networks for data classification
6.1 Neural networks
6.1.1 Background and evolution of neural networks
6.1.2 Working of neural networks
6.1.3 Neural networks for data classification
6.1.3.1 Advantages
6.1.3.2 Applications
6.1.4 Characteristics of neural networks
6.2 Different types of neural networks
6.2.1 Feedforward neural network
6.2.1.1 Applications
6.2.1.1.1 Multilayered feedforward neural network
6.2.2 Radial basis function neural network
6.2.3 Multilayer perceptron
6.2.4 Convolutional neural network
6.2.4.1 Application
6.2.5 Recurrent neural network
6.2.6 Modular neural network
6.2.6.1 Advantages of modular neural networks
6.2.7 Artificial neural network
6.2.7.1 Advantages
6.2.7.2 Applications
6.2.8 Fuzzy neural network
6.2.9 Probabilistic neural network
6.3 Training of neural network
6.4 Training algorithms in neural network for data classification
6.4.1 Backpropagation algorithm
6.4.2 Genetic algorithm
6.4.3 Levenberg–Marquardt algorithm
References
7 Application of artificial intelligence in the perspective of data mining
7.1 Artificial intelligence
7.1.1 Artificial neural networks
7.1.2 Fuzzy logic
7.1.3 Genetic algorithm
7.1.4 Expert system
7.1.5 Hybrid systems
7.2 Artificial intelligence versus data mining
7.3 Modeling theory based on artificial intelligence and data mining
7.3.1 Modeling, prediction, and forecasting of artificial intelligence using solar radiation data
7.3.2 Modeling of artificial intelligence in the environmental systems
7.3.2.1 Case-based reasoning
7.3.2.2 Rule-based system
7.3.2.3 Reinforcement learning
7.3.2.4 Multiagent systems
7.3.3 Integration of artificial intelligence into water quality modeling
7.3.4 Modeling of the offset lithographic printing process
7.3.5 Modeling human teaching tactics and strategies for tutoring systems
7.3.6 Modeling of artificial intelligence for engine idle speed system and control optimization
7.3.7 Data mining approach for modeling sediment transport
7.3.8 Modeling of artificial intelligence for monitoring flood defense structures
7.3.8.1 Data-driven approach
7.3.8.2 Model-based approach
7.3.9 Modeling of artificial intelligence in intelligent manufacturing system
7.3.9.1 Resources or capabilities layer
7.3.9.2 Ubiquitous network layer
7.3.9.3 Service platform layer
7.3.9.4 General technology
7.3.9.5 Intelligent manufacturing platform technology
7.3.9.6 Ubiquitous network technology
7.3.9.7 Product life cycle manufacturing technology
7.3.9.8 Supporting technology
7.3.10 Constitutive modeling of cemented paste backfill
7.3.11 Spontaneous reporting system modeling for data mining methods evaluation in pharmacovigilance
7.3.11.1 Summary
References
8 Biomedical data mining for improved clinical diagnosis
8.1 Introduction
8.2 Descriptions and features of data mining
8.3 Revolution of data mining
8.4 Data mining for healthcare
8.4.1 Applications for mining healthcare data
8.4.1.1 Hospital infection control
8.4.1.2 Ranking hospitals
8.4.1.3 Identification of high-risk patients
8.4.1.4 Diagnosis and prediction of diseases
8.4.1.5 Effective treatments
8.4.1.6 Best quality services provided to the patients
8.4.1.7 Insurance abuse and fraud reduction
8.4.1.8 Appropriate hospital resource management
8.4.1.9 Better treatment approaches
8.5 Data mining for biological application
8.5.1 DNA sequence analysis
8.5.2 Protein sequence analysis
8.5.3 Gene expression analysis
8.5.4 Gene association analysis
8.5.5 Macromolecule structure analysis
8.5.6 Genome analysis
8.5.7 Pathway analysis
8.5.8 Microarray analysis
8.5.9 Computational modeling of biological networks
8.5.9.1 Biological networks
8.5.9.2 Modeling of networks
8.6 Data mining for disease diagnosis
8.6.1 Neural network for heart disease diagnosis
8.6.2 Apriori algorithm for frequent disease
8.6.3 Bayesian network modeling for psychiatric diseases
8.6.4 Adaptive fuzzy k-nearest neighbor approach for Parkinson’s disease diagnosis
8.7 Data mining of drug discovery
8.7.1 Target identification
8.7.2 Target validation and hit identification
8.7.3 Hit to lead
8.7.4 Lead optimization
8.7.5 Late-stage drug discovery and clinical trials
References
9 Satellite data: big data extraction and analysis
9.1 Remote-sensing data: properties and analysis
9.1.1 Satellite sensors
9.1.1.1 Advanced Very High-Resolution Radiometer
9.1.1.2 Landsat Multi-Spectral Scanner
9.1.1.3 Landsat Thematic Mapper
9.1.1.4 Landsat Enhanced Thematic Mapper Plus
9.1.2 Data resolution characteristics
9.1.2.1 Spatial resolution
9.1.2.2 Spectral resolution
9.1.2.3 Radiometric resolution
9.1.2.4 Temporal resolution
9.1.3 Data representation
9.1.3.1 Vector data type
9.1.3.1.1 ESRI shapefile vector file format
9.1.3.1.2 Census 200 Topologically Integrated Geographic Encoding and Referencing (TIGER)/Line vector file format
9.1.3.1.3 Data description
9.1.3.1.4 Software functionality
9.1.3.1.5 Advantages of vector data
9.1.3.2 Raster data type
9.1.3.2.1 Band Interleaved by Pixel
9.1.3.2.2 Band interleaved by line
9.1.3.2.3 Band Sequential
9.1.3.2.4 Advantages of raster data
9.1.4 Data mining or extraction
9.1.4.1 Spatial data mining
9.1.4.2 Temporal data mining
9.1.4.2.1 Representations of temporal data
9.1.4.2.2 Time domain–based representations
9.1.4.2.3 Transformation-based representations
9.1.4.2.4 Generative model–based representations
9.1.4.3 Spatiotemporal data mining
9.1.5 Big data mining for remote-sensing data
9.1.6 Big data mining methods for social welfare application
9.1.6.1 A data mining approach for heavy rainfall forecasting based on satellite image sequence analysis
9.1.6.2 Using spatial reinforcement learning to build forest wildfire dynamics models from satellite images
9.1.6.3 Improved density–based spatial clustering of applications of noise clustering algorithm for knowledge discovery in ...
9.1.6.4 Data mining algorithms for land cover change detection: a review
9.1.6.5 An autonomous forest fire detection system based on spatial data mining and fuzzy logic
9.1.6.6 System refinement for content-based satellite image retrieval
9.1.6.7 Automated detection of clouds in satellite imagery
9.2 Summary
References
10 Advancement of data mining methods for improvement of agricultural methods and productivity
10.1 Agriculture data: properties and analysis
10.1.1 Data representation
10.1.1.1 Process-mediated
10.1.1.2 Machine generated
10.1.1.3 Human sourced
10.1.2 Data management
10.1.2.1 Sensing and monitoring
10.1.2.2 Analysis and decision-making
10.1.2.3 Intervention
10.1.2.4 Data capture
10.1.2.5 Data storage
10.1.2.6 Data transfer
10.1.2.7 Data transformation
10.1.2.8 Data marketing
10.1.3 Irrigation management using data mining
10.1.3.1 Field capacity
10.1.3.2 Permanent wilting point
10.1.3.3 Soil density
10.1.3.4 Fuzzy neural network for irrigation management
10.1.3.5 Forecast the crop yield
10.1.3.5.1 DT method for predicting climate parameters
10.1.3.5.2 Artificial neural networks for wheat yield forecasting
10.1.3.6 Estimation of the precise amount of water and suggestion of the necessary fertilizers
10.1.3.7 Prediction of the irrigation events
10.1.3.8 Minimization of irrigation cost
10.1.3.9 Accurate suggestion of plants for the soil
10.1.3.9.1 Alluvial soils
10.1.3.9.2 Black soils
10.1.3.9.3 Laterite soils
10.1.3.9.4 Mountain soils
10.1.3.9.5 Red and yellow soils
10.1.3.9.6 Other soils
10.1.3.10 Measurement of growth rate
10.1.3.10.1 Determinate growth
10.1.3.10.2 Indeterminate growth
10.1.3.11 Growth rate analysis
10.1.3.11.1 Crop growth rate
10.1.3.11.2 Absolute growth rate
10.1.3.11.3 Relative growth rate
10.1.3.11.4 Growth index
10.1.3.12 Water body prediction for better crop filed
10.2 Disease prediction using data mining
10.2.1 Crop disease prediction
10.2.2 Rice plant disease prediction
10.2.3 Leaf disease prediction
10.2.4 Plant disease prediction
10.3 Pests monitoring using data mining
10.3.1 Pest control methods
10.3.2 NNs algorithm for pest monitoring
10.3.3 RF algorithm for pest monitoring
10.4 Summary
References
11 Advanced data mining for defense and security applications
11.1 Military data: properties and analysis
11.1.1 Data source
11.1.1.1 Radar data
11.1.1.2 Airborne data
11.1.1.3 Military communication signal data
11.1.1.4 Weapon data
11.1.2 Data protection strategies
11.1.2.1 Data obfuscation
11.1.2.2 Data anonymization
11.1.2.3 Data privacy protection
11.1.2.3.1 K-anonymity
11.1.2.3.2 L-diversity
11.1.2.3.3 T-closeness
11.1.2.3.4 Randomization technique
11.1.2.3.5 Data distribution technique
11.1.2.4 Data encryption
11.2 Applying data mining for military application
11.2.1 Data mining application in navy flight and maintenance data to affect flight repair
11.2.2 Data mining methods used in online military training
11.2.3 A data mining approach to enhance military demand forecasting
11.2.4 Architecture of knowledge discovery engine for military commanders using massive runs of simulations
11.2.4.1 Rule discovery algorithm
11.2.4.2 Bayesian network
11.2.5 Adaptive immune genetic algorithm for weapon system optimization in a military big data environment
11.2.6 Application of data mining analysis to assess military ground vehicle components
11.2.6.1 Data mining and analysis process
11.2.7 Data mining model in proactive defense of cyber threats
11.2.7.1 Synthetic attack generation
11.2.8 Modeling adaptive defense against cybercrimes with real-time data mining
11.2.8.1 Information security technologies
11.2.8.2 Real-time data mining
11.2.8.3 Summary
References
Index
Back Cover