By specializing in a vertical market, companies can better understand their customers and bring more insight to clients in order to become an integral part of their businesses. This approach requires dedicated tools, which is where artificial intelligence (AI) and machine learning (ML) will play a major role. By adopting AI software and services, businesses can create predictive strategies, enhance their capabilities, better interact with customers, and streamline their business processes.
This edited book explores novel concepts and cutting-edge research and developments towards designing these fully automated advanced digital systems. Fostered by technological advances in artificial intelligence and machine learning, such systems potentially have a wide range of applications in robotics, human computing, sensing and networking. The chapters focus on models and theoretical approaches to guarantee automation in large multi-scale implementations of AI and ML systems; protocol designs to ensure AI systems meet key requirements for future services such as latency; and optimisation algorithms to leverage the trusted distributed and efficient complex architectures.
The book is of interest to researchers, scientists, and engineers working in the fields of ICTs, networking, AI, ML, signal processing, HCI, robotics and sensing. It could also be used as supplementary material for courses on AI, machine and deep learning, ICTs, networking signal processing, robotics and sensing.
Author(s): Muhammad Zeeshan Shakir, Naeem Ramzan
Series: Computing and Networks
Publisher: Institution of Engineering & Technology
Year: 2021
Language: English
Pages: 384
City: London
Contents
About the editors
Preface
Part I: Human–robot
1. Deep learning techniques for modelling human manipulation and its translation for autonomous robotic grasping with soft end-effectors | Visar Arapi, Yujie Zhang, Giuseppe Averta, Cosimo Della Santina, and Matteo Bianchi
1.1 Introduction
1.2 Investigation of the human example
1.3 Autonomous grasping with anthropomorphic soft hands
1.4 Discussion and conclusions
Acknowledgement
References
2. Artificial intelligence for affective computing: an emotion recognition case study | Pablo Arnau-González, Stamos Katsigiannis, Miguel Arevalillo-Herráez, and Naeem Ramzan
2.1 Introduction
2.2 Models of human affect
2.3 Previous work on emotion recognition
2.4 Data sets for emotion recognition
2.5 Proposed methodology
2.6 Experimental results
2.7 Conclusions and discussion
Acknowledgement
References
3. Machine learning-based affect detection within the context of human–horse interaction | Turke Althobaiti, Stamos Katsigiannis, DauneWest, Hassan Rabah, and Naeem Ramzan
3.1 Introduction
3.2 Background
3.3 Experimental protocol
3.4 Analysis of captured data
3.5 Experimental results
3.6 Discussion
3.7 Conclusion
References
4. Robot intelligence for real-world applications | Eleftherios Triantafyllidis, Chuanyu Yang, Christopher McGreavy, Wenbin Hu, and Zhibin Li
4.1 Introduction
4.2 Novel robotic applications in locomotion
4.3 Novel robotic applications in human-guided manipulation
4.4 Novel robotic applications in fully autonomous manipulation
4.5 Conclusion
References
5. Visual object tracking by quadrotor AR.Drone using artificial neural networks and fuzzy logic controller | Kamel Boudjit, Cherif Larbes and Naeem Ramzan
5.1 Introduction
5.2 System overview
5.3 Fuzzy-logic-based identification and target tracking
5.4 Artificial neural networks (ANN) for target identification and tracking using a quadrotor
5.5 Conclusion
References
Part II: Network
6. Predictive mobility management in cellular networks | Metin Öztürk, Paulo Valente Klaine, Sajjad Hussain, and Muhammad Ali Imran
6.1 Introduction
6.2 Mobility management in cellular networks
6.3 Predictive mobility management
6.4 Advanced Markov-chain-assisted predictive mobility management
6.5 Summary
References
7. Artificial intelligence and data analytics in 5G and beyond-5G wireless networks | Maziar Nekovee, Dehao Wu, YueWang and Mehrdad Shariat
7.1 Introduction
7.2 Case studies of AI in 5G wireless networks
7.3 Data analytics in 5G
7.4 Industry and standard activities
7.5 Challenges and open questions
7.6 Conclusions
References
8. Deep Q-network-based coverage hole detection for future wireless networks | Shahriar Abdullah Al-Ahmed, Muhammad Zeeshan Shakir,and Qasim Zeeshan Ahmed
8.1 Introduction
8.2 Machine learning
8.3 System model
8.4 DQN-based coverage hole detection
8.5 Simulation results and discussion
8.6 Conclusions
References
9. Artificial intelligence for localization of ultrawide bandwidth (UWB) sensor nodes | Fuhu Che, Abbas Ahmed, Qasim Zeeshan Ahmed, and Muhammad Zeeshan Shakir
9.1 Introduction
9.2 Indoor positioning system
9.3 UWB ranging accuracy evaluation
9.4 Implementation and evaluation
9.5 Conclusion
References
10. A Cascaded Machine Learning Approach for indoor classification and localization using adaptive feature selection | Mohamed I. AlHajri, Nazar T. Ali and Raed M. Shubair
10.1 Introduction
10.2 Indoor radio propagation channel
10.3 Data collection phase: practical measurements campaign
10.4 Signatures of indoor environment
10.5 Spatial correlation coefficient
10.6 Machine learning algorithms
10.7 Cascaded Machine Learning Approach
10.8 Conclusion
References
Part III: Sensing
11. EEG-based biometrics: effects of template ageing | Pablo Arnau-González, Stamos Katsigiannis, Miguel Arevalillo-Herraez and Naeem Ramzan
11.1 Introduction
11.2 Background
11.3 Data acquisition and experimental protocol
11.4 Experimental results
11.5 Conclusions
References
12. A machine-learning-driven solution to the problem of perceptual video quality metrics | Stamos Katsigiannis, Hassan Rabah, and Naeem Ramzan
12.1 Introduction
12.2 Objective video quality assessment methods
12.3 The video multimethod assessment fusion (VMAF) metric
12.4 Experimental evaluation
12.5 Conclusion
References
13. Multitask learning for autonomous driving | Murtaza Taj and Waseem Abbas
13.1 Introduction
13.2 Related work
13.3 Problem formulation
13.4 Driving parameter estimation
13.5 Scene understanding
13.6 Computational complexity
13.7 Summary
References
14 Machine-learning-enabled ECG monitoring for early detection of hyperkalaemia | Constance Farrell and Muhammad Zeeshan Shakir
14.1 Introduction
14.2 ECG signal analysis
14.3 ECG data collection and preprocessing
14.4 Machine learning classification models
14.5 Results
14.6 Conclusions and recommendations
References
15. Combining deterministic compressed sensing and machine learning for data reduction in connected health | Hassan Rabah, Slavisa Jovanovic and Naeem Ramzan
15.1 Introduction
15.2 Background and related work
15.3 Method
15.4 Experimental results and discussion
15.5 Conclusion
References
16. Large-scale distributed and scalable SOM-based architecture for high-dimensional data reduction | Slavisa Jovanovic, Hassan Rabah, and SergeWeber
16.1 Introduction
16.2 Related work
16.3 Background
16.4 Proposed SOM model
16.5 Results and discussion
16.6 Conclusion
References
17. Surface water pollution monitoring using the Internet of Things (IoT) and machine learning | Hamza Khurshid, Rafia Mumtaz, Noor Alvi, Faisal Shafait, Sheraz Ahmed, Muhammad Imran Malik, Andreas Dengel, and Quanita Kiran
17.1 Introduction
17.2 Literature review
17.3 Methodology
17.4 Results and discussion
17.5 Conclusion and future work
Acknowledgment
References
18. Conclusions
Index
