255. Automated classification of Resting State fMRI networks using Machine Learning algorithms

Inattention is one of the most significant clinical symptoms for evaluating attention deficit hyperactivity disorder (ADHD). Previous inattention estimations were performed using clinical scales. Recently, predictive models for inattention have been established for brain-behavior estimation using neuroimaging features. However, the performance of inattention estimation could be improved for conventional brain-behavior models with additional feature selection, machine learning algorithms, and validation procedures. This paper aimed to propose a unified framework for inattention estimation from resting state fMRI to improve the classical brain-behavior models. Phase synchrony was derived as raw features, which were selected with minimum-redundancy maximum-relevancy (mRMR) method. Six machine learning algorithms were applied as regression methods. 100 runs of 10-fold cross-validations were performed on the ADHD-200 datasets. The relevance vector machines (RVMs) based on the mRMR features for the brain-behavior models significantly improve the performance of inattention estimation. The mRMR-RVM models could achieve a total accuracy of 0.53. Furthermore, predictive patterns for inattention were discovered by the mRMR technique. We found that the bilateral subcortical-cerebellum networks exhibited the most predictive phase synchrony patterns for inattention. Together, an optimized strategy named mRMR-RVM for brain-behavior models was found for inattention estimation. The predictive patterns might help better understand the phase synchrony mechanisms for inattention.

Download Full-text

ISOMAP and machine learning algorithms for the construction of embedded functional connectivity networks of anatomically separated brain regions from resting state fMRI data of patients with Schizophrenia

AIMS Neuroscience ◽

10.3934/neuroscience.2021016 ◽

2021 ◽

Vol 8 (2) ◽

pp. 295-321

Author(s):

Ioannis K Gallos ◽

◽

Kostakis Gkiatis ◽

George K Matsopoulos ◽

Constantinos Siettos ◽

...

Keyword(s):

Machine Learning ◽

Functional Connectivity ◽

Resting State ◽

Learning Algorithms ◽

Resting State Fmri ◽

Brain Regions ◽

Machine Learning Algorithms ◽

Fmri Data

Download Full-text

Evaluation of machine learning algorithms performance for the prediction of early multiple sclerosis from resting-state FMRI connectivity data

Brain Imaging and Behavior ◽

10.1007/s11682-018-9926-9 ◽

2018 ◽

Vol 13 (4) ◽

pp. 1103-1114 ◽

Cited By ~ 9

Author(s):

Valeria Saccà ◽

Alessia Sarica ◽

Fabiana Novellino ◽

Stefania Barone ◽

Tiziana Tallarico ◽

...

Keyword(s):

Machine Learning ◽

Multiple Sclerosis ◽

Resting State ◽

Learning Algorithms ◽

Resting State Fmri ◽

Machine Learning Algorithms

Download Full-text

Machine Learning Approach for Automatic Detection of Alzheimers Disease using Resting State fMRI

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.36170 ◽

2021 ◽

Vol 9 (VI) ◽

pp. 5399-5409

Author(s):

K. Emily Esther Rani

Keyword(s):

Machine Learning ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Early Diagnosis ◽

Resting State ◽

Learning Algorithms ◽

Resting State Fmri ◽

Machine Learning Algorithms ◽

Support Vector ◽

Discrete Wavelet

Alzheimer’s Disease (AD) is a neurological disease that affects memory and the livelihood of the people that are diagnosed with it. Efficient automated techniques for early diagnosis of AD is very important because early diagnosis is used to prevent a patient from death. In this work, we present a novel computer-aided diagnosis (CAD) techniques using machine learning algorithms for the early diagnosis of AD. The input resting state fMRI(rsfMRI) images are taken from Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. The input image is pre-processed using Discrete Wavelet Transform(DWT). Automated thresholding algorithm is used to segment the image. Then, the segmented resting state fMRI images are used to extract useful and informative features. The best features are selected by Fisher’s code feature selection algorithm. Finally, an automated Image classification step is performed using machine learning algorithms Support Vector Machine(SVM), Decision Tree , Random Forest and Multi-Layer Perceptron algorithms to distinguish between normal patients and AD patients.

Download Full-text

174 A comparison of machine learning algorithms in the classification of beef steers finished in feedlot

Journal of Animal Science ◽

10.1093/jas/skaa278.231 ◽

2020 ◽

Vol 98 (Supplement_4) ◽

pp. 126-127

Author(s):

Lucas S Lopes ◽

Christine F Baes ◽

Dan Tulpan ◽

Luis Artur Loyola Chardulo ◽

Otavio Machado Neto ◽

...

Keyword(s):

Machine Learning ◽

Decision Tree ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Final Decision ◽

Relevant Parameter ◽

Good Prediction ◽

Quality Traits ◽

C4.5 Decision Tree

Abstract The aim of this project is to compare some of the state-of-the-art machine learning algorithms on the classification of steers finished in feedlots based on performance, carcass and meat quality traits. The precise classification of animals allows for fast, real-time decision making in animal food industry, such as culling or retention of herd animals. Beef production presents high variability in its numerous carcass and beef quality traits. Machine learning algorithms and software provide an opportunity to evaluate the interactions between traits to better classify animals. Four different treatment levels of wet distiller’s grain were applied to 97 Angus-Nellore animals and used as features for the classification problem. The C4.5 decision tree, Naïve Bayes (NB), Random Forest (RF) and Multilayer Perceptron (MLP) Artificial Neural Network algorithms were used to predict and classify the animals based on recorded traits measurements, which include initial and final weights, sheer force and meat color. The top performing classifier was the C4.5 decision tree algorithm with a classification accuracy of 96.90%, while the RF, the MLP and NB classifiers had accuracies of 55.67%, 39.17% and 29.89% respectively. We observed that the final decision tree model constructed with C4.5 selected only the dry matter intake (DMI) feature as a differentiator. When DMI was removed, no other feature or combination of features was sufficiently strong to provide good prediction accuracies for any of the classifiers. We plan to investigate in a follow-up study on a significantly larger sample size, the reasons behind DMI being a more relevant parameter than the other measurements.

Download Full-text

Classification of Daily Irradiance Profiles and the Behaviour of Photovoltaic Plant Elements: The Effects of Cloud Enhancement

Applied Sciences ◽

10.3390/app11115230 ◽

2021 ◽

Vol 11 (11) ◽

pp. 5230

Author(s):

Isabel Santiago ◽

Jorge Luis Esquivel-Martin ◽

David Trillo-Montero ◽

Rafael Jesús Real-Calvo ◽

Víctor Pallarés-López

Keyword(s):

Machine Learning ◽

Learning Algorithms ◽

Automatic Classification ◽

Sampling Frequency ◽

Machine Learning Algorithms ◽

Unsupervised Machine Learning ◽

Average Efficiency ◽

Clear Sky ◽

Photovoltaic Plant

In this work, the automatic classification of daily irradiance profiles registered in a photovoltaic installation located in the south of Spain was carried out for a period of nine years, with a sampling frequency of 5 min, and the subsequent analysis of the operation of the elements of the installation on each type of day was also performed. The classification was based on the total daily irradiance values and the fluctuations of this parameter throughout the day. The irradiance profiles were grouped into nine different categories using unsupervised machine learning algorithms for clustering, implemented in Python. It was found that the behaviour of the modules and the inverter of the installation was influenced by the type of day obtained, such that the latter worked with a better average efficiency on days with higher irradiance and lower fluctuations. However, the modules worked with better average efficiency on days with irradiance fluctuations than on clear sky days. This behaviour of the modules may be due to the presence, on days with passing clouds, of the phenomenon known as cloud enhancement, in which, due to reflections of radiation on the edges of the clouds, irradiance values can be higher at certain moments than those that occur on clear sky days, without passing clouds. This is due to the higher energy generated during these irradiance peaks and to the lower temperatures that the module reaches due to the shaded areas created by the clouds, resulting in a reduction in its temperature losses.

Download Full-text

Mapping Allochemical Limestone Formations in Hazara, Pakistan Using Google Cloud Architecture: Application of Machine-Learning Algorithms on Multispectral Data

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10020058 ◽

2021 ◽

Vol 10 (2) ◽

pp. 58

Author(s):

Muhammad Fawad Akbar Khan ◽

Khan Muhammad ◽

Shahid Bashir ◽

Shahab Ud Din ◽

Muhammad Hanif

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Learning Algorithms ◽

Remote Sensing Data ◽

Kappa Coefficient ◽

Machine Learning Algorithms ◽

Landsat 8 ◽

Sensing Data ◽

Fossiliferous Limestone

Low-resolution Geological Survey of Pakistan (GSP) maps surrounding the region of interest show oolitic and fossiliferous limestone occurrences correspondingly in Samanasuk, Lockhart, and Margalla hill formations in the Hazara division, Pakistan. Machine-learning algorithms (MLAs) have been rarely applied to multispectral remote sensing data for differentiating between limestone formations formed due to different depositional environments, such as oolitic or fossiliferous. Unlike the previous studies that mostly report lithological classification of rock types having different chemical compositions by the MLAs, this paper aimed to investigate MLAs’ potential for mapping subclasses within the same lithology, i.e., limestone. Additionally, selecting appropriate data labels, training algorithms, hyperparameters, and remote sensing data sources were also investigated while applying these MLAs. In this paper, first, oolitic (Samanasuk), fossiliferous (Lockhart and Margalla) limestone-bearing formations along with the adjoining Hazara formation were mapped using random forest (RF), support vector machine (SVM), classification and regression tree (CART), and naïve Bayes (NB) MLAs. The RF algorithm reported the best accuracy of 83.28% and a Kappa coefficient of 0.78. To further improve the targeted allochemical limestone formation map, annotation labels were generated by the fusion of maps obtained from principal component analysis (PCA), decorrelation stretching (DS), X-means clustering applied to ASTER-L1T, Landsat-8, and Sentinel-2 datasets. These labels were used to train and validate SVM, CART, NB, and RF MLAs to obtain a binary classification map of limestone occurrences in the Hazara division, Pakistan using the Google Earth Engine (GEE) platform. The classification of Landsat-8 data by CART reported 99.63% accuracy, with a Kappa coefficient of 0.99, and was in good agreement with the field validation. This binary limestone map was further classified into oolitic (Samanasuk) and fossiliferous (Lockhart and Margalla) formations by all the four MLAs; in this case, RF surpassed all the other algorithms with an improved accuracy of 96.36%. This improvement can be attributed to better annotation, resulting in a binary limestone classification map, which formed a mask for improved classification of oolitic and fossiliferous limestone in the area.

Download Full-text