Technology is currently a crucial benchmark in any application area. In general, society is immersed in the era of digitalization; therefore, incorporating digital technology in different application areas has been more accessible. Nowadays, claiming that adopting artificial intelligence systems in any area is already an emerging need. In this chapter, several artificial intelligence techniques are presented, as well as algorithms and tools that have been used to provide a variety of solutions such as artificial neural networks, convolutional neural networks architecture, AI models, machine learning, deep learning, and bio-inspired algorithms focused mainly on ant colony optimization, response threshold models, and stochastic learning automata. Likewise, the main applications that use AI techniques are described, and the main trends in this discipline are mentioned. This chapter ends with a critical discussion of artificial intelligence advances.
TopIntroduction
Artificial Intelligence (AI) has had incredible growth since its beginnings until today. Significant progress has been made in different applications, such as computer vision, speech recognition, robotics, semantic parsing, transfer learning, natural language processing, machine learning, and deep learning. In general, there are different fields of application of artificial intelligence; the classification of these fields is directly related to four main areas. First, Natural Language Processing, where the main objective is to capture, process, and respond in natural language to make the machines understand human speech, both speaking and writing (Grisot, 2018). Second, through Image Processing or Computer Vision is possible to capture, store, and edit images using different algorithms to perform the analysis (Bhowmik, 2018). Third, using Robotics, it can create computer-controlled mechanical systems that allow performing a variety of different tasks (Waidyasekara, 2020). Fourth, to collect, store, and process various information to derive recommendations or instructions to act on Expert Systems is necessary (Singholi, 2018).
Robotics is one of the most characteristic areas of AI; numerous advances have been developed that have allowed contributing to different areas of application. Traditionally, robotics applications focused on mainly in the industrial sector. In the last two decades, the field of application of robotics has been extended to other sectors, for example, robots for construction, domestic robots, assistance robots, robots in medicine, robots defense, rescue and security (Waidyasekara, 2020). In the last years, automation and control have become a topic of interest for researchers from different areas. mainly, the industrial robotics (Grau, 2017; Yenorkar, 2018) and in the robotic systems applied in the medical area, such as tele-operated surgery (Burgner-Kahrs, 2015) and surgical pattern cutting (Murali, 2015). currently, there are continuous technological developments and various applications such as prostheses (Allen, 2016), orthoses (Niyetkaliyev, 2017), exoskeletons (Tehmat, 2018), and devices for teleoperation to improve human capabilities (Quiñonez, 2020a).
Also, Unmanned Aerial Vehicles (UAV) has been an object mainly study in autonomous exploration in urban environments, exploration, and generation of three-dimensional maps. In this sense, calculating the appropriate movements for a machine to reach a specific point in space is a great challenge. Some works have been developed that focus on the execution of complex algorithms to obtain solutions related to autonomous navigation using reactive algorithms (Quiñonez, 2018), and images classification in real time using convolutional neural networks (Quiñonez, 2020b). On the other hand, Computer Vision (CV) has a multitude of applications in different areas (Rashed, 2019; Kumar, 2019). Certainly, robotics is one of the primary beneficiaries (Ansari, 2020a), because computer vision is one of the most used techniques based on image analysis (Rohan, 2019). Several techniques form the computer vision field, and besides that, they are consistently combined with machine learning algorithms (Ansari, 2020b). In the last decades, pattern recognition has become an exciting research line in the area of robotics and computer vision (Quiñonez, 2015). The classical techniques of pattern recognition more used are template matching, statistical classification, syntactic or structural matching, and neural networks.
The remainder of this paper is organized as follows: section background introduces an overview of previous related works on the application of different techniques of AI, such as IoT applications, machine learning, deep learning, and the most common application domains. In the section of techniques, algorithms, and tools; the main AI techniques, the characteristics, the applications, the different algorithms, and the architectures used for each of the techniques are described in detail. Also, different artificial intelligence platforms are mentioned that allow developers to create their projects in a faster and easier way. In section future trends, a summary of artificial intelligence trends is presented according to the Accenture Technology Vision 2019 Report. Finally, the conclusion section, it summarizes the conclusions of the paper.