scholarly journals A novel method to estimate model uncertainty using machine learning techniques

2009 ◽  
Vol 45 (12) ◽  
Author(s):  
Dimitri P. Solomatine ◽  
Durga Lal Shrestha
Keyword(s):  
Machine Learning ◽  
Model Uncertainty ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Novel Method

scholarly journals Two-dimensional multifibre spectral image correction based on machine learning techniques

2020 ◽  
Vol 499 (2) ◽  
pp. 1972-1984
Author(s):  
Jiali Xu ◽  
Qian Yin ◽  
Ping Guo ◽  
Xin Zheng
Keyword(s):  
Machine Learning ◽  
Spatial Variation ◽  
Blind Deconvolution ◽  
Machine Learning Techniques ◽  
Image Correction ◽  
Point Spread Functions ◽  
Learning Techniques ◽  
Before And After ◽  
Novel Method ◽  
Spatially Variant

ABSTRACT Owing to the limited size and imperfections of the optical components in a spectrometer, aberrations inevitably make their way into 2D multifibre spectral images in the Large Sky Area Multi-Object Fiber Spectroscopy Telescope (LAMOST), which leads to obvious spatial variation of the point spread functions (PSFs). However, if spatially variant PSFs are estimated directly, the large storage and intensive computational requirements result in the deconvolution spectrum extraction method becoming intractable. In this paper, we propose a novel method to solve the problem of spatial variation of the PSFs through image aberration correction. When CCD image aberrations are corrected, the convolution kernel can be approximated by only one spatially invariant PSF. Specifically, a novel method based on machine learning is proposed to calibrate the distorted spectral images. The method includes many techniques, such as total least squares (TLS) algorithm, self-supervised learning and multilayer feed-forward neural networksnetworks, and it makes use of a special training set sampling scheme combining 2D distortion features in a flat-field spectrum and calibration lamp spectrum. The calibration experiments on the LAMOST CCD images show that the proposed method is feasible. Furthermore, the spectrum extraction results before and after calibration are compared, and the experimental results show that the characteristics of the extracted 1D waveform are closer to those of an ideal optics system after image correction, and that the PSF of the corrected object spectrum estimated by the blind deconvolution method is nearly centrosymmetric, which indicates that our proposed method can significantly reduce the complexity of spectrum extraction and improve extraction accuracy.

A Novel Approach to Detect Spam and Smishing SMS using Machine Learning Techniques

2021 ◽  
pp. 267-285
Author(s):  
Ankit Kumar Jain ◽  
Sumit Kumar Yadav ◽  
Neelam Choudhary
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Second Phase ◽  
Short Message ◽  
Machine Learning Classifiers ◽  
Novel Approach ◽  
Learning Techniques ◽  
Message Service ◽  
Novel Method ◽  
Two Phases

Smishing attack is generally performed by sending a fake short message service (SMS) that contains a link of the malicious webpage or application. Smishing messages are the subclass of spam SMS and these are more harmful compared to spam messages. There are various solutions available to detect the spam messages. However, no existing solution, filters the smishing message from the spam message. Therefore, this article presents a novel method to filter smishing message from spam message. The proposed approach is divided into two phases. The first phase filters the spam messages and ham messages. The second phase filters smishing messages from spam messages. The performance of the proposed method is evaluated on various machine learning classifiers using the dataset of ham and spam messages. The simulation results indicate that the proposed approach can detect spam messages with the accuracy of 94.9% and it can filter smishing messages with the accuracy of 96% on neural network classifier.

A Novel Approach to Detect Spam and Smishing SMS using Machine Learning Techniques

2020 ◽  
Vol 12 (1) ◽  
pp. 21-38 ◽  
Author(s):  
Ankit Kumar Jain ◽  
Sumit Kumar Yadav ◽  
Neelam Choudhary
Keyword(s):  
Machine Learning ◽  
Short Message Service ◽  
Machine Learning Techniques ◽  
Second Phase ◽  
Short Message ◽  
Novel Approach ◽  
Learning Techniques ◽  
Message Service ◽  
Novel Method ◽  
Two Phases

Smishing attack is generally performed by sending a fake short message service (SMS) that contains a link of the malicious webpage or application. Smishing messages are the subclass of spam SMS and these are more harmful compared to spam messages. There are various solutions available to detect the spam messages. However, no existing solution, filters the smishing message from the spam message. Therefore, this article presents a novel method to filter smishing message from spam message. The proposed approach is divided into two phases. The first phase filters the spam messages and ham messages. The second phase filters smishing messages from spam messages. The performance of the proposed method is evaluated on various machine learning classifiers using the dataset of ham and spam messages. The simulation results indicate that the proposed approach can detect spam messages with the accuracy of 94.9% and it can filter smishing messages with the accuracy of 96% on neural network classifier.

scholarly journals Effective Cardiovascular Disease Prediction using Hybrid Machine Learning Techniques

2020 ◽  
Vol 9 (4) ◽  
pp. 1555-1558
Keyword(s):  
Machine Learning ◽  
Cardiovascular Disease ◽  
Heart Disease ◽  
Accurate Diagnosis ◽  
Machine Learning Techniques ◽  
Disease Prediction ◽  
Naked Eye ◽  
The People ◽  
Learning Techniques ◽  
Novel Method

In today’s era deaths due to heart disease has become a major issue approximately one person dies per minute due to heart disease. This is considering both male and female category and this ratio may vary according to the region also this ratio is considered for the people of different age groups.Heart disease is one of the most fatal problems in the whole world, which cannot be seen with a naked eye and comes instantly when its limitations are reached.There are various data mining and machine learning techniques and tools available to extract effective knowledge from databases and to use this knowledge for more accurate diagnosis and decision making.In this paper, we propose a novel method that aims at finding significant features by applying machine learning techniques resulting in improving the accuracy in the prediction of cardiovascular disease. We produce an enhanced performance level with an accuracy through the prediction model for heart disease with the proposed method hybrid random forest with a linear model.In this paper commonly used machine learning techniques and their complexities are summarized.

scholarly journals Heart Disease Prediction using Machine Learning and Data Mining

2020 ◽  
Vol 9 (1) ◽  
pp. 21-219
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Heart Diseases ◽  
Machine Learning Techniques ◽  
K Nearest Neighbors ◽  
Learning Techniques ◽  
Rapid Pace ◽  
Novel Method ◽  
Unbalanced Diet ◽  
Major Factors

Weighing only 300 grams, Heart is declining the mortality rate at a rapid pace from decades. The major factors that contribute to it are smoking, drinking, unbalanced diet, and many more. Even with these more technical advancements the analysis of the clinical data is a critical challenge. With the use of Machine Learning techniques, it is possible to analyse the data and interpret the cause that lead to heart diseases such as Coronary Heart Disease, Arrhythmia, and Dilated Cardiomyopathy. Many researchers are developing IoT enabled hardware to predict these diseases using various ML and DM techniques. In this study, we propose a novel method to determine the disease using Cleveland Heart Disease Dataset by combining the computational power of various ML and DM algorithms and concluded that among all the algorithms, K-Nearest Neighbors gives the highest accuracy of 87%. Along with this, a web app is developed using flask in python with which the user can enter the attributes and predict the heart disease.

scholarly journals Accurately constraining velocity information from spectral imaging observations using machine learning techniques

2020 ◽  
Vol 379 (2190) ◽  
pp. 20200171 ◽  
Author(s):  
Conor D. MacBride ◽  
David B. Jess ◽  
Samuel D. T. Grant ◽  
Elena Khomenko ◽  
Peter H. Keys ◽  
...  
Keyword(s):  
Machine Learning ◽  
Spectral Imaging ◽  
Spectral Lines ◽  
Machine Learning Techniques ◽  
Line Profiles ◽  
Wave Dynamics ◽  
Learning Techniques ◽  
Spectral Components ◽  
Velocity Information ◽  
Novel Method

Determining accurate plasma Doppler (line-of-sight) velocities from spectroscopic measurements is a challenging endeavour, especially when weak chromospheric absorption lines are often rapidly evolving and, hence, contain multiple spectral components in their constituent line profiles. Here, we present a novel method that employs machine learning techniques to identify the underlying components present within observed spectral lines, before subsequently constraining the constituent profiles through single or multiple Voigt fits. Our method allows active and quiescent components present in spectra to be identified and isolated for subsequent study. Lastly, we employ a Ca ɪɪ 8542 Å spectral imaging dataset as a proof-of-concept study to benchmark the suitability of our code for extracting two-component atmospheric profiles that are commonly present in sunspot chromospheres. Minimization tests are employed to validate the reliability of the results, achieving median reduced χ 2 -values equal to 1.03 between the observed and synthesized umbral line profiles. This article is part of the Theo Murphy meeting issue ‘High-resolution wave dynamics in the lower solar atmosphere’.

A novel method for sentiment classification of drug reviews using fusion of deep and machine learning techniques

2020 ◽  
Vol 198 ◽  
pp. 105949 ◽  
Author(s):  
Mohammad Ehsan Basiri ◽  
Moloud Abdar ◽  
Mehmet Akif Cifci ◽  
Shahla Nemati ◽  
U. Rajendra Acharya
Keyword(s):  
Machine Learning ◽  
Sentiment Classification ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Novel Method

Using machine learning techniques to reduce data annotation time

2006 ◽  
Author(s):  
Christopher Schreiner ◽  
Kari Torkkola ◽  
Mike Gardner ◽  
Keshu Zhang
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Data Annotation ◽  
Learning Techniques

Using Machine Learning Algorithms on Prediction of Stock Price

2020 ◽  
Vol 12 (2) ◽  
pp. 84-99
Author(s):  
Li-Pang Chen
Keyword(s):  
Machine Learning ◽  
Stock Price ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Short Term ◽  
Learning Techniques ◽  
Historical Database ◽  
Long Short Term Memory

In this paper, we investigate analysis and prediction of the time-dependent data. We focus our attention on four different stocks are selected from Yahoo Finance historical database. To build up models and predict the future stock price, we consider three different machine learning techniques including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) and Support Vector Regression (SVR). By treating close price, open price, daily low, daily high, adjusted close price, and volume of trades as predictors in machine learning methods, it can be shown that the prediction accuracy is improved.

Sign in / Sign up

Export Citation Format

Share Document