Artificial Intelligence and Data Science in Environmental Sensing

Front Cover
Artificial Intelligence and Data Science in Environmental Sensing
Artificial Intelligence and Data Science in Environmental Sensing
Copyright
Contents
Contributors
Editor Bio
Preface
1 - Smart sensing technologies for wastewater treatment plants
1. Introduction
2. Online estimation
3. Fault detection and diagnostics
3.1 Electrochemical sensors
3.2 Fiber optic sensors for direct monitoring of water quality
3.3 Sensors based on microwave technology
4. Multivariate analysis models
5. Conclusion and future direction
References
2 - Advancements and artificial intelligence approaches in antennas for environmental sensing
1. Printed antennas for wireless sensor networks
2. Printed antenna sensors for material characterization
3. Epidermal antenna for unobtrusive human-centric wireless communications and sensing
3.1 Epidermal electronics
3.2 Epidermal antennas
3.2.1 Compensated radio frequency performance
3.2.2 Induced health and safety issue
3.2.3 Imposed additional physical requirements
4. Artificial intelligence in antenna design
4.1 Particle swarm optimization in antenna design
4.2 Artificial neural network in antenna design
References
3 - Intelligent geo-sensing for moving toward smart, resilient, low emission, and less carbon transport
1. Introduction
2. The role of transport in the economy and environment
3. Geo-sensing; evolution in the geography
4. Geographic Information System as a revolution or/and an evolution
5. Geo-sensing for moving toward eco-routing and low-emission transport
6. Intelligent geo-sensing and AI as a new window to the future
7. Conclusion
References
4 - Language of response surface methodology as an experimental strategy for electrochemical wastewater treatment p ...
1. Introduction
2. Strategy of response surface methodology
3. Practical application of RSM in electrochemical processes for wastewater treatment
3.1 Electrocoagulation
3.2 Electro-Fenton
3.3 Electro-oxidation
3.4 Hybrid processes
4. Merits and demerits of RSM
5. Conclusions
References
5 - Artificial intelligence and sustainability: solutions to social and environmental challenges
1. Introduction
2. AI and social change: the case of food and garden waste management
2.1 AI-powered analysis of FOGO survey data
2.2 Using AI insights to improve waste management
3. AI and ecosystem services: insights into bushfire management and renewable energy production
3.1 AI role in predicting bushfire occurrence and spread
3.2 Artificial intelligence for energy conservation and renewable energy
4. Challenges of using AI to achieve sustainability
5. Implications and conclusion
References
6 - Application of multi-criteria decision-making tools for a site analysis of offshore wind turbines
1. Decision-making in renewable energy investments
2. Decision-making tools on the development and design of offshore wind power farms
3. Background of multiattribute decision-making tools
3.1 VIKOR (VlseKriterijumska Optimizacija I Kompromisno Resenje)
3.2 PROMETHEE (Preference Ranking Organization Method for Enrichment Evaluation)
3.3 ELECTRE (ELimination Et Choice Translating REality)
4. Background of multiobjective problems in offshore and wind farms
4.1 Practical studies
4.2 Objectives and solution methods
4.3 Future directions
References
7 - Recent advances of image processing techniques in agriculture
1. Introduction
2. Application in plants detection
2.1 Plant segmentation and extraction in the field
2.2 Plant diseases recognition
2.2.1 Datasets and problem setting
2.2.2 Conventional machine learning methods
2.2.3 Deep learning methods
2.2.4 Transfer learning methods
2.2.5 Analysis of effectiveness
2.3 Three-dimensional monitoring for plant growth
3. Application in livestock recognition
3.1 Livestock detection
3.2 Cattle recognition
3.2.1 Muzzle point image pattern
3.2.2 Coat pattern
3.2.3 Rear view
3.2.4 Multiviews face
4. Application in fruits and vegetables recognition
4.1 Fruits and vegetables identification and classification
4.2 Fruits and vegetables grading and sorting
4.3 Fruits and vegetables disease and defect detection
5. Conclusion
References
8 - Tuning swarm behavior for environmental sensing tasks represented as coverage problems
1. Introduction
2. Preliminaries
2.1 Related work
2.2 Reynolds' boid model
2.3 Reinforcement learning
2.4 Coverage problems
3. System design: swarming for coverage tasks
3.1 Autonomous tuning of swarm behavior by the reinforcement learning subsystem
3.2 Coverage algorithm subsystem
4. Experimental analysis
4.1 Experiment 1: learning to tune a swarm
4.1.1 Experimental setup
4.1.2 Results
4.2 Experiment 2: using a tuned swarm to solve a coverage problem
4.2.1 Experimental setup
4.2.2 Results
4.3 Evaluating the tuning and coverage ability of RL-SBAT on unseen random boids
4.3.1 Experimental setup
4.3.2 Results
4.4 Evaluating the tuning and coverage ability of RL-SBAT on unseen random movement of robots
4.4.1 Experimental setup
4.4.2 Results
5. Conclusions and future work
Appendix
References
9 - Machine learning applications for developing sustainable construction materials
1. Introduction
2. Prediction
2.1 Fresh properties
2.2 Mechanical properties
2.3 Durability
3. Damage segmentation and detection
4. Mixture design
5. Multiobjective optimization
6. Conclusions
References
10 - The AI-assisted removal and sensor-based detection of contaminants in the aquatic environment
1. Introduction
2. AI-assisted techniques for PFAS detection and removal
3. Sensors for detection of PFAS
3.1 Electrochemical sensors
3.2 Optical and fluorescence sensors
4. Biosensors
5. Disinfection by-products
5.1 AI-assisted techniques for disinfection by-products removal
5.2 Sensors for detection of DBPs
5.3 Heavy metals
6. AI-assisted techniques for removal of heavy metal
6.1 Sensors for detection of heavy metals
6.2 Antibiotics, endocrine-disrupting chemicals/pharmaceuticals
6.2.1 AI-assisted techniques for removal of antibiotics, endocrine-disrupting chemicals/pharmaceuticals
6.3 Sensors for detection of heavy metals antibiotics, endocrine-disrupting chemicals/pharmaceuticals
References
11 - Recent progress in biosensors for wastewater monitoring and surveillance
1. Introduction
2. Principles and working of BES as a biosensor
2.1 Microbial fuel cell as a sensor
2.2 Microbial electrolysis cell as a sensor
3. Biosensor for various pollutant monitoring
3.1 Organic pollutants
3.2 Nitrogen pollutants
3.3 Toxic pollutants
4. Photoelectrochemical biosensors
4.1 Photoelectrochemical enzymatic biosensors
5. Biosensors as a perspective to monitor infectious disease outbreak
6. Conclusions, future trends, and prospective of biosensors
References
12 - Machine learning in surface plasmon resonance for environmental monitoring
1. Introduction
2. Surface plasmon resonance
2.1 Sensorgram
2.2 Other types of SPR platforms
3. Environmental hazard monitoring by SPR
3.1 Detection of pesticides
3.2 Detection of phenolic compounds
3.3 Detection of heavy metal ions
3.4 Detection of pathogen microorganisms
4. Machine learning algorithms in SPR
4.1 Supervised machine learning
4.1.1 Κ-Nearest neighbor
4.1.2 Ridge regression
4.1.3 Feedforward artificial neural networks
4.1.4 Convolutional neural network
4.1.5 Deep neural network
4.1.6 Genetic algorithm–based artificial neural networks
4.1.7 Generative adversarial network
4.2 Unsupervised machine learning
4.2.1 K-means clustering
4.2.2 Principal component analysis
4.2.3 T-distributed stochastic neighbor embedding
4.2.4 Autoencoder
4.2.5 Clustering using representatives
4.2.6 Non-negative matrix factorization
5. Applications of ML in SPR
6. Conclusion and future perspectives
References
Index
A
B
C
D
E
F
G
H
I
K
L
M
N
O
P
Q
R
S
T
U
V
W
Back Cover