Applied Biomedical Engineering Using Artificial Intelligence and Cognitive Models - Chapter 6 - dataset -Deep Learning Models Evolution Applied to Biomedical Engineering

In this chapter we focus on studying “Deep Learning Models Evolution” that combine midlevel elements with different connections “ANN” types to form more complex network types such as “Recurrent Neural Networks,” “Memory Augmented Neural Networks,” “Modular Neural Networks,” and “Evolutive Neural Networks". Please read this chapter at Science Direct: https://www.sciencedirect.com/science/article/pii/B978012820718500012X or buy the book/eBook at Elsevier, Amazon, and Bookstore worldwide.
Section 6.2.3.1 Research 6.1 LSTM to classify videos about human body movements and detect human falls (folder MATLAB_LTSM_videos)
Section 6.2.5.1 Research 6.2 Regional-CNN model for object detection of breast tumor in mammogram (folder MATLAB_R-CNN)
Section 6.2.6.1 Research 6.3 Hopfield Network model to reconstruct noisy chest X-ray images (folder MATLAB_HN)
Section 6.2.8.1 Research 6.4 Restricted Boltzmann Machine model to reconstruct noisy chest X-ray images (folder MATLAB_RBM)
Section 6.2.10.1 Research 6.5 Create a Reservoir Computing approach for a simulation of “Liquid State Machine (LSM)” of node neurons from “Spiking Neural Networks (SNN)” based on the “Izhikevich neuronal mathematical model” to differentiate normal and pneumonia on chest X-rays (folder MATLAB_LSM)
Section 6.3.2.1 Research 6.6 simulation of a Turing Machine (TM) using a recursive function to "analyze how the respiratory transmission of a COVID-19 infected person can spread a virus through droplets/mini-droplets emissions" (folder MATLAB_NTM)
Section 6.4.1.1 Research 6.7 Create a Deep Belief Network model to analyze and differentiate normal and pneumonia chest X-rays. “DBN model” from MATLAB based on node neurons from “Spiking Neural Networks (SNN)” applying the “Siegert Neurons mathematical model” to “differentiate normal and pneumonia chest X-rays” (folder MATLAB_DBN)
Note*: Please see an “Attention Networks” example at Chapter 7, Research 7.2 “Attention network using Long/Short-Term Memory to Classify Text of COVID-19 symptoms”.

本章专注于探讨融合中层次元素与不同“ANN”类型连接的“深度学习模型演化”研究，旨在构建诸如“循环神经网络”、“记忆增强神经网络”、“模块化神经网络”以及“进化神经网络”等更为复杂的网络架构。请参阅Science Direct上的本章内容：https://www.sciencedirect.com/science/article/pii/B978012820718500012X，或在Elsevier、Amazon及全球书店购买本书/eBook。

第6.2.3.1节 研究第6.1节：利用LSTM对关于人体运动的视频进行分类并检测跌倒事件（文件夹：MATLAB_LTSM_videos）

第6.2.5.1节 研究第6.2节：提出一种针对乳腺肿瘤在钼靶图像中的目标检测的“区域-CNN”模型（文件夹：MATLAB_R-CNN）

第6.2.6.1节 研究第6.3节：使用Hopfield网络模型重建带有噪声的胸部X光图像（文件夹：MATLAB_HN）

第6.2.8.1节 研究第6.4节：采用受限玻尔兹曼机模型重建带有噪声的胸部X光图像（文件夹：MATLAB_RBM）

第6.2.10.1节 研究第6.5节：创建一种基于“液态机（LSM）”的节点神经元模拟方法，该方法以“Izhikevich神经元数学模型”为基础，从“脉冲神经网络（SNN）”出发，用于区分胸部X光图像中的正常与肺炎情况（文件夹：MATLAB_LSM）

第6.3.2.1节 研究第6.6节：利用递归函数模拟图灵机（TM），以“分析COVID-19感染者通过飞沫/微飞沫排放如何传播病毒”为研究目标（文件夹：MATLAB_NTM）

第6.4.1.1节 研究第6.7节：创建一种深度信念网络模型，用于分析和区分胸部X光图像中的正常与肺炎情况。该模型基于“Siegert神经元数学模型”，由MATLAB中的节点神经元构成，应用于“区分胸部X光图像中的正常与肺炎情况”（文件夹：MATLAB_DBN）

注：请参考第7章中的“注意力网络”示例，研究第7.2节：“使用长/短时记忆的注意力网络对COVID-19症状文本进行分类”