Applied Biomedical Engineering Using Artificial Intelligence and Cognitive Models

Applied Biomedical Engineering Using Artificial Intelligence and Cognitive Models focuses on the relationship between three different multidisciplinary branches of engineering: Biomedical Engineering, Cognitive Science and Computer Science through Artificial Intelligence models. These models will be used to study how the nervous system and musculoskeletal system obey movement orders from the brain, as well as the mental processes of the information during cognition when injuries and neurologic diseases are present in the human body.

The interaction between these three areas are studied in this book with the objective of obtaining AI models on injuries and neurologic diseases of the human body, studying diseases of the brain, spine and the nerves that connect them with the musculoskeletal system. There are more than 600 diseases of the nervous system, including brain tumors, epilepsy, Parkinson's disease, stroke, and many others. These diseases affect the human cognitive system that sends orders from the central nervous system (CNS) through the peripheral nervous systems (PNS) to do tasks using the musculoskeletal system. These actions can be detected by many Bioinstruments (Biomedical Instruments) and cognitive device data, allowing us to apply AI using Machine Learning-Deep Learning-Cognitive Computing models through algorithms to analyze, detect, classify, and forecast the process of various illnesses, diseases, and injuries of the human body.

Applied Biomedical Engineering Using Artificial Intelligence and Cognitive Models provides readers with the study of injuries, illness, and neurological diseases of the human body through Artificial Intelligence using Machine Learning (ML), Deep Learning (DL) and Cognitive Computing (CC) models based on algorithms developed with MATLAB® and IBM Watson®.

• Provides an introduction to Cognitive science, cognitive computing and human cognitive relation to help in the solution of AI Biomedical engineering problems
• Explain different Artificial Intelligence (AI) including evolutionary algorithms to emulate natural evolution, reinforced learning, Artificial Neural Network (ANN) type and cognitive learning and to obtain many AI models for Biomedical Engineering problems
• Includes coverage of the evolution Artificial Intelligence through Machine Learning (ML), Deep Learning (DL), Cognitive Computing (CC) using MATLAB® as a programming language with many add-on MATLAB® toolboxes, and AI based commercial products cloud services as: IBM (Cognitive Computing, IBM Watson®, IBM Watson Studio®, IBM Watson Studio Visual Recognition®), and others
• Provides the necessary tools to accelerate obtaining results for the analysis of injuries, illness, and neurologic diseases that can be detected through the static, kinetics and kinematics, and natural body language data and medical imaging techniques applying AI using ML-DL-CC algorithms with the objective of obtaining appropriate conclusions to create solutions that improve the quality of life of patients

Reference for Academic research on: Biomedical Engineering, Biomechatronics, Applied Informatics, Bioinformatics, Biomechanics, Neural Engineering, Clinical Engineering, Rehabilitation Engineering, Applied Mathematics, computational intelligence, Medical devices and many others, besides specific practical applications in Human computer interaction, cognitive robotics, cognitive ergonomics and cognitive engineering.

Chapter I. Biomedical Engineering and the evolution of Artificial Intelligence

• Evolution of Artificial intelligence (AI) through Machine Learning (ML), Deep Learning (DL), Cognitive Computing (CC) using MATLAB(r)and AI-based commercial products cloud services as: IBM (Cognitive Computing under IBM Watson®), and others.
• Introduction to the general framework architecture for AI- Cognitive Computing Agent Systems (AI-CCAS) to help in the detection of cognitive human-like abilities with the objective of develop AI methods for medicine and healthcare through the analysis of numeric data, images, speech, and text to help in the detection and diagnostic of illness or determine health conditions.

Chapter II. Introduction to Cognitive science, cognitive computing and human cognitive relation to help in the solution of AI Biomedical engineering problems.

• Study of the human brain structure and functions and their relation to AI and CC.
• Focusing on the process of human cognition as the mental action of acquiring knowledge and understanding through thought, experience and the senses and their relation to AI and CC.　
• Natural Language Processing (NLP) examples and exercise as: NLP Topics, Audio Labeler for Machine Learning, NLP Text to speech, NLP Speech to Text, NLP analysis for: Sentiment, Emotion, Keywords, Entities, Categories, Concept and Semantic Roles with MATLAB™ and API a set of functions and procedures allowing the creation of applications that access the features or data of an operating system, application, or other service through IBM Cloud™ services.

• Artificial Intelligence and Biomedical Engineering: concepts, models, algorithms, and examples.　
• Problem solving methodologies: Search-based approaches, Heuristic search, Search for optimization, Constraint satisfaction, and others.
• Genetic Algorithms for AI Optimization in Biomedical Engineering.
• Examples of Applications of Evolutionary Algorithms with others AI tools for Biomedical Engineering solutions using MATLAB™ and IBM Watson Studio SPSS Model Flow.

• Machine Learning is studied as a subset of AI following the typical algorithm steps to obtain a prediction model based in pattern recognition in data using clustering, classifiers, and regression models.
• Advices to follow, select, find, and implement the best ML Models, accordingly of the type of machine learning problem.
• ML types: Unsupervised Learning, Supervised Learning, Reinforcement Learning, Survival Models, Association Rules, and others.
• Study of different ML Models Families applying IBM Watson™ SPSS Modeler Flow / IBM Watson Machine Learning™ applications and MATLAB™ ML solution under the Statistics and Machine Learning Toolbox™, with research tutorial examples to analyses an obtain prediction models for different biomedical datasets.

• Underlying principle of deep learning is a compositional nature of neural network inspired by the biological elements that forms the human brain, as a collection of nodes emulating brain neurons, and their neuron synapses connections as primary elements of a net, that combined form mid-level elements identified as artificial neural networks (ANN), which in turn are combined with different architectures to form more complex networks.
• ANN are organized based on their architectural type, and the way of their different components are connected to one another to define the specific learning goal as different types as: feed forward neural network, backpropagation neural networks, recurrent neural networks, memory augmented neural networks, modular neural networks and evolutive neural networks.
• The first two ANN types: feed forward neural and backpropagation are studied in deep in this chapter plus a general net shallow neural network, and special kind of learning known as transfer learning from pretrained deep learning networks. All based on examples and practical researches on Biomedical Engineering using existing AI tools.
• Study and examples for ANN: perceptron, multi-layer perceptron’s, radial basis function network, probabilistic neural network, extreme learning machine, auto encoders, variational auto encoder, denoising auto encoder, sparse auto encoder & stacked auto encoders, deep convolution network, deconvolutional network, deep convolutional inverse graphics network, generative adversarial network, deep residual network and others.

• This chapter focus to study deep learning models evolution that combined mid-level elements with different connections ANN to form more complex networks types as: recurrent neural networks, memory augmented neural networks, modular neural networks and evolutive neural networks.
• Study and examples for ANN: recurrent neural network vanilla, long/short term memory, long/short term memory, gated recurrent unit, recurrent convolutional neural networks, regional-convolutional neural network, Hopfield network, Boltzmann machine, restricted Boltzmann machine, liquid state machine, echo state network, Korhonen network also knows as self-organizing map, neural turning machine, differentiable neural computers, deep belief network, capsule networks, attention network, and others.
• Many researches as examples are studied applied to Biomedical Engineering solutions.

• In this chapter we will focus on many pre-studies and pre-analysis of different biomedical engineering problems that need to be develop with specialized research projects applying cognitive learning & reasoning algorithm, that can be integrated to the proposed general architecture framework of a cognitive computing agents system (AI-CCAS) with special emphasis at "Cognitive Learning and its relationship with neuroscience of reasoning proposed as Cognitive Learning- Reasoning using Cognitive Computing".
• The AI cognitive models to be used for the AI-CCAS are studied in this chapter are: inference engine to extract information needed from knowledge storage AI storage, attention network for NLP applying long short-term memory model to process information extracted by the AI-CCAS inference engine, cognitive learning & reasoning using deductive reasoning, inductive reasoning, abductive reasoning, metaphoric reasoning, neuro-fuzzy logic reasoning, visuo-spatial relational reasoning, inferences fuzzy systems for fuzzy reasoning, cognitive sentiments analysis, reasoning evaluation for neurologic diseases, and others
• Ten Challenge research to develop applications from Applied Biomedical Engineering using Artificial Intelligence and Cognitive Models learned in this book.