A machine learning approach of finding the optimal anisotropic SPH kernel

Abstract It is presented a machine learning approach to find the optimal anisotropic SPH kernel, whose compact support consists of an ellipsoid that matches with the convex hull of the self-regulating k-nearest neighbors of the smoothing particle (query).

Download Full-text

Machine Learning Approach to Dysphonia Detection

Applied Sciences ◽

10.3390/app8101927 ◽

2018 ◽

Vol 8 (10) ◽

pp. 1927 ◽

Cited By ~ 1

Author(s):

Zuzana Dankovičová ◽

Dávid Sovák ◽

Peter Drotár ◽

Liberios Vokorokos

Keyword(s):

Machine Learning ◽

State Of The Art ◽

Nearest Neighbors ◽

Classification Model ◽

Support Vector ◽

Learning Approach ◽

K Nearest Neighbors ◽

Machine Learning Methods ◽

Machine Learning Approach ◽

Speech Features

This paper addresses the processing of speech data and their utilization in a decision support system. The main aim of this work is to utilize machine learning methods to recognize pathological speech, particularly dysphonia. We extracted 1560 speech features and used these to train the classification model. As classifiers, three state-of-the-art methods were used: K-nearest neighbors, random forests, and support vector machine. We analyzed the performance of classifiers with and without gender taken into account. The experimental results showed that it is possible to recognize pathological speech with as high as a 91.3% classification accuracy.

Download Full-text

SENTIMENT ANALYSIS OF COVID-19 TWEETS

FUDMA Journal of Sciences ◽

10.33003/fjs-2021-0501-690 ◽

2021 ◽

Vol 5 (1) ◽

pp. 566-576

Author(s):

Azeez A. Nureni ◽

Victor E. Ogunlusi ◽

Emmanuel Junior Uloko

Keyword(s):

Machine Learning ◽

Sentiment Analysis ◽

Nearest Neighbors ◽

Support Vector ◽

Classification Algorithms ◽

Learning Approach ◽

K Nearest Neighbors ◽

Machine Learning Classification ◽

Global Pandemic ◽

Machine Learning Approach

Sentiment analysis involves techniques used in analyzing texts in order to identify the sentiment and emotion dominant in such texts and classify them accordingly. Techniques involved include but not limited to preprocessing of texts and the use a machine learning or lexical based approach in classifying these texts. In this research, attempt was made to adopt a machine learning approach to classify tweets on Covid-19 which is considered a global pandemic. To achieve this noble objective, a cross-dataset approach was applied to train four machine learning classification algorithms: Support Vector Machine (SVM), Random Forest (RF) and Naïve Bayes (NB), as well as K-Nearest Neighbors algorithm (KNN). The final result will not only assist us in knowing the best performing algorithm, it will also assist in creating awareness on Covid-19 with the final objective of destigmatizing the patients through the analysis of sentiments and emotions on Covid-19 and finally use the same result for containing the spread of the pandemic

Download Full-text

An Innovative Machine Learning Approach to Predict the Dietary Fiber Content of Packaged Foods

Nutrients ◽

10.3390/nu13093195 ◽

2021 ◽

Vol 13 (9) ◽

pp. 3195

Author(s):

Tazman Davies ◽

Jimmy Chun Yu Louie ◽

Tailane Scapin ◽

Simone Pettigrew ◽

Jason HY Wu ◽

...

Keyword(s):

Machine Learning ◽

Dietary Fiber ◽

Large Scale ◽

Learning Algorithm ◽

Fiber Content ◽

Learning Approach ◽

K Nearest Neighbors ◽

Machine Learning Approach ◽

Packaged Foods ◽

Prediction Approach

Underconsumption of dietary fiber is prevalent worldwide and is associated with multiple adverse health conditions. Despite the importance of fiber, the labeling of fiber content on packaged foods and beverages is voluntary in most countries, making it challenging for consumers and policy makers to monitor fiber consumption. Here, we developed a machine learning approach for automated and systematic prediction of fiber content using nutrient information commonly available on packaged products. An Australian packaged food dataset with known fiber content information was divided into training (n = 8986) and test datasets (n = 2455). Utilization of a k-nearest neighbors machine learning algorithm explained a greater proportion of variance in fiber content than an existing manual fiber prediction approach (R2 = 0.84 vs. R2 = 0.68). Our findings highlight the opportunity to use machine learning to efficiently predict the fiber content of packaged products on a large scale.

Download Full-text

Machine learning approach for accurate backmapping of coarse-grained models to all-atom models

Chemical Communications ◽

10.1039/d0cc02651d ◽

2020 ◽

Vol 56 (65) ◽

pp. 9312-9315 ◽

Cited By ~ 2

Author(s):

Yaxin An ◽

Sanket A. Deshmukh

Keyword(s):

Neural Network ◽

Machine Learning ◽

Artificial Neural Network ◽

Random Forest ◽

Regression Models ◽

Gaussian Process Regression ◽

Nearest Neighbors ◽

Coarse Grained ◽

Learning Approach ◽

Machine Learning Approach

Four different machine learning (ML) regression models: artificial neural network, k-nearest neighbors, Gaussian process regression and random forest were built to backmap coarse-grained models to all-atom models.

Download Full-text