10 promising AI books coming in 2023
Advances in Swarm Intelligence
Anupam Biswas, Can B. Kalayci, Seyedali Mirjalili
The idea of swarm intelligence was defined in 1989 in scientific society in the context of cellular robotic systems, but it was described earlier (1964) in science fiction.
Briefly speaking, swarm intelligence systems contain many boids (agents) interacting with one another and their environment. Every boid has a set of simple rules and there is no central “brain” in the system. But local random interactions between boids create system behavior that can be called “intelligent” and is uncontrollable for a single boid.
Swarm intelligence is a part of nature-inspired algorithms and is often used for optimization, for example, Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC), and Glowworm Swarm Optimization (GSO).
This book has an introductory chapter, an engineering one, and a machine learning one that should cover all the aspects of the topic.
Sustainable Smart Cities
Pradeep Kumar Singh, Marcin Paprzycki, Mohamad Essaaidi, Shahram Rahimi
Smart cities, mostly, are not very “smart” for an artificial intelligence developer. Usually, city-level algorithms are way behind recent research. Of course, the root of it is bureaucracy and the high cost of improvements so changes come rather slow nowadays. But let’s think about how can modern solutions be applied to smart cities.
This book covers topics of IoT, Blockchain, and other latest technologies.
Emotional Artificial Intelligence and Metaverse
Roger Lee
I guess every developer had a period of his career (or studies) when he was dreaming of taking part in the invention of emotional AI. Not many of us ended up making these romantic dreams come true, but with the recently announced metaverses may start being interested in this field again.
This book presents the scientific results of the 1st ACIS International Symposium on Emotional Artificial Intelligence & Metaverse where researchers, and it’s definitely worth reading since the promising future of this technology.
Handbook on Decision Making. Trends and Challenges in Intelligent Decision Support Systems.
Julian Andres Zapata-Cortes, Cuauhtémoc Sánchez-Ramírez, Giner Alor-Hernández, Jorge Luis García-Alcaraz
Decision Support Theory and Systems was my favorite class in university and I believe it was the most everyday-life applicable one, so I couldn’t pass by this book. This book is not for noobies since it is a set of conference papers, actually it’s recommended for Ph.D. level. But you can find many life examples here such as Bitcoin Price Forecasting, Detecting Arrhythmia Using the IoT, or Emotion Detection in Learning Environments Using Facial Expressions.
Nature-Inspired Intelligent Computing Techniques in Bioinformatics
Khalid Raza
Nature-inspired computing (NIC) can be a super-interesting field for those who think technology is opposing nature.
This book covers future perspectives of NIC techniques in bioinformatics, such as genomic profiling, personalized therapy complications, antimicrobial resistance in bacterial pathogens, computer-aided drug design, cancer detection, disease biomarkers, and other topics that can be inspiring for any developer who is bored with business tasks that don’t bring real value for the humanity.
Multimodal AI in Healthcare
Arash Shaban-Nejad, Martin Michalowski, Simone Bianco
One more book on AI in healthcare since it’s one of the most profitable fields which got even more respected after the COVID-19 outbreak.
This book contains selected papers presented at the 2022 Health Intelligence workshop and the associated Data Hackathon/Challenge, co-located with the Thirty-Sixth Association for the Advancement of Artificial Intelligence (AAAI).
Engineering Applications of Modern Metaheuristics
Taymaz Akan, Ahmed M. Anter, A. Şima Etaner-Uyar, Diego Oliva
A metaheuristic is a high-level problem-independent algorithmic framework that provides a set of guidelines or strategies to develop heuristic optimization algorithms (Sörensen and Glover, 2013). Algorithms are not problem-specific, approximate, and usually non-deterministic.
This book is a collection of various methodologies that make it possible for metaheuristics and hyper-heuristics to solve problems that occur in the real world. The application fields range from image processing to transmission power control, some chapters present cutting-edge methods for load frequency control and IoT implementations. The researchers used several stochastic optimization methods in this book, including evolutionary algorithms and Swarm-based algorithms.
Predictive Data Security using AI. Insights and Issues of Blockchain, IoT, and DevOps
Hiren Kumar Thakkar, Mayank Swarnkar, Robin Singh Bhadoria
Data security and AI? Maybe not that obvious but why not?
This book discusses the security aspects of the latest technologies such as Blockchain, IoT, and DevOps, and how to effectively deal with them using Intelligent techniques. Moreover, machine learning (ML) and deep learning (DL) algorithms are also not secured and often manipulated by attackers for data stealing and this book offers novel solutions to counter the attacks.
Explainable Edge AI: A Futuristic Computing Perspective
Aboul Ella Hassanien, Deepak Gupta, Anuj Kumar Singh, Ankit Garg
The issues of transparency, fairness, accountability, explainability, interpretability, data-fusion, and comprehensibility are significant for edge AI. Explainable AI (XAI) is a set of processes and methods that allows human users to comprehend and trust the results and output created by machine learning algorithms, as well as improve the algorithms and productivity in the final result. In the futuristic computing scenario, the goal of explainable AI (XAI) will be to execute the AI tasks and produce explainable results at the edge.
AI Time Series Control System Modelling
Chuzo Ninagawa
I bet time series predictions were one of the first in your pet projects when you tried to detect the stock market patterns and predict future shares’ prices. But of course, the time series are spread much wider.
This book explains how to build control models from time-series data using machine learning. It is essential to predict the change from the present to the future based on the time history of each variable in the target system and to manipulate the system to achieve the desired change.
