Journal: Neural Regeneration Research

Article Title: Decoding degeneration: the implementation of machine learning for clinical detection of neurodegenerative disorders

doi: 10.4103/1673-5374.355982

Figure Lengend Snippet: An overview of the step-by-step process by which machine learning and computer-aided diagnosis techniques process and analyze clinical and neuroimaging data to identify features associated with neurodegenerative diseases. First, images and clinical data are processed, and features of interest are identified. Then, the identified features are extracted and cross-validated across data types. The machine learning model establishes patterns in the training dataset that can be used to classify or make predictions based on any comparable future dataset. Created with BioRender.com. MMSE: Mini-Mental State Examination.

Article Snippet: Liu et al., 2014 , AD/CN classification , Extraction of complementary information from multimodal neuroimaging data , Stacked SAE and Softmax regression layer , 87%.

Techniques: Biomarker Discovery

Journal: Neural Regeneration Research

Article Title: Decoding degeneration: the implementation of machine learning for clinical detection of neurodegenerative disorders

doi: 10.4103/1673-5374.355982

Figure Lengend Snippet: ML algorithms developed for the classification of AD, CN, and MCI over the past ten years and their accuracies

Article Snippet: Liu et al., 2014 , AD/CN classification , Extraction of complementary information from multimodal neuroimaging data , Stacked SAE and Softmax regression layer , 87%.

Techniques: Extraction

Journal: Sensors (Basel, Switzerland)

Article Title: Brain MRI Analysis for Alzheimer’s Disease Diagnosis Using CNN-Based Feature Extraction and Machine Learning

doi: 10.3390/s22082911

Figure Lengend Snippet: Summary and comparison of the selected recent research.

Article Snippet: Liu et al. (2015) [ ] , stacked auto-encoder SAE + Softmax , 91.40 , 90.42% , 92.32%.

Techniques: Comparison, Selection, T-Test, Generated

Journal: Sensors (Basel, Switzerland)

Article Title: Brain MRI Analysis for Alzheimer’s Disease Diagnosis Using CNN-Based Feature Extraction and Machine Learning

doi: 10.3390/s22082911

Figure Lengend Snippet: Comparison of our test performance with eight existing state-of-the-art methods.

Article Snippet: Liu et al. (2015) [ ] , stacked auto-encoder SAE + Softmax , 91.40 , 90.42% , 92.32%.

Techniques: Comparison

Journal: Current Research in Food Science

Article Title: Machine learning techniques for analysis of hyperspectral images to determine quality of food products: A review

doi: 10.1016/j.crfs.2021.01.002

Figure Lengend Snippet: Deep Learning (DL) applications in hyperspectral image analysis of food products.

Article Snippet: Detection and quantification of nitrogen content in rapeseed leaf , 400–1000 , – , Image thresholding , Stacked auto-encoders (SAE) and fully-connected neural network (FNN) , Feature extraction from hyperspectral data through SAE , Input for FNN: SAE extracted features , 80:20 , MATLAB 8.1; PYTHON , 90% , .

Techniques: Biomarker Discovery, Software, Activation Assay, Control, Extraction

Journal: Computational Intelligence and Neuroscience

Article Title: An Improved Stacked Autoencoder for Metabolomic Data Classification

doi: 10.1155/2021/1051172

Figure Lengend Snippet: Fine-tuning structure (SAE, stacked autoencoder).

Article Snippet: In this study, we aimed to introduce an improved framework, named Hessian-free [ ] stacked autoencoder (HF-SAE), combining the Hessian-free algorithm and SAE model with Softmax regression for the classification of metabolomic data of NR-treated RA.

Techniques:

Journal: Computational Intelligence and Neuroscience

Article Title: An Improved Stacked Autoencoder for Metabolomic Data Classification

doi: 10.1155/2021/1051172

Figure Lengend Snippet: Fine-tuning of experimental results on the five-fold data sets. The red and blue lines represent the GD-SAE and HF-SAE results, respectively. In each subgraph of (a) to (e), (i) shows the FMSE, (ii) shows the CR of the training set, and (iii) shows the CR of the test set (GD-SAE, gradient descent stacked autoencoder; HF-SAE, Hessian-free SAE; FMSE, fine-tuning mean square error; CR, classification rate).

Article Snippet: In this study, we aimed to introduce an improved framework, named Hessian-free [ ] stacked autoencoder (HF-SAE), combining the Hessian-free algorithm and SAE model with Softmax regression for the classification of metabolomic data of NR-treated RA.

Techniques: