scholarly journals Ensemble Learning of Convolutional Neural Network, Support Vector Machine, and Best Linear Unbiased Predictor for Brain Age Prediction: ARAMIS Contribution to the Predictive Analytics Competition 2019 Challenge

2020 ◽  
Vol 11 ◽  
Author(s):  
Baptiste Couvy-Duchesne ◽  
Johann Faouzi ◽  
Benoît Martin ◽  
Elina Thibeau–Sutre ◽  
Adam Wild ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Ensemble Learning ◽  
Predictive Analytics ◽  
Disease Status ◽  
Absolute Error ◽  
Training Sample ◽  
Support Vector ◽  
Best Linear Unbiased Predictor ◽  
Brain Images ◽  
Best Linear Unbiased

We ranked third in the Predictive Analytics Competition (PAC) 2019 challenge by achieving a mean absolute error (MAE) of 3.33 years in predicting age from T1-weighted MRI brain images. Our approach combined seven algorithms that allow generating predictions when the number of features exceeds the number of observations, in particular, two versions of best linear unbiased predictor (BLUP), support vector machine (SVM), two shallow convolutional neural networks (CNNs), and the famous ResNet and Inception V1. Ensemble learning was derived from estimating weights via linear regression in a hold-out subset of the training sample. We further evaluated and identified factors that could influence prediction accuracy: choice of algorithm, ensemble learning, and features used as input/MRI image processing. Our prediction error was correlated with age, and absolute error was greater for older participants, suggesting to increase the training sample for this subgroup. Our results may be used to guide researchers to build age predictors on healthy individuals, which can be used in research and in the clinics as non-specific predictors of disease status.

scholarly journals Searching for Prosociality in Qualitative Data: Comparing Manual, Closed–Vocabulary, and Open–Vocabulary Methods

2020 ◽  
Vol 34 (5) ◽  
pp. 903-916
Author(s):  
William H.B. McAuliffe ◽  
Hannah Moshontz ◽  
Thomas G. McCauley ◽  
Michael E. McCullough
Keyword(s):  
Support Vector Machine ◽  
European Association ◽  
Qualitative Data ◽  
Support Vector Machine Classifier ◽  
Goal Pursuit ◽  
Training Sample ◽  
Support Vector ◽  
Personality Psychology ◽  
Self Presentation ◽  
Personal Strivings

Although most people present themselves as possessing prosocial traits, people differ in the extent to which they actually act prosocially in everyday life. Qualitative data that were not ostensibly collected to measure prosociality might contain information about prosocial dispositions that is not distorted by self–presentation concerns. This paper seeks to characterise charitable donors from qualitative data. We compared a manual approach of extracting predictors from participants’ self–described personal strivings to two automated approaches: A summation of words predefined as prosocial and a support vector machine classifier. Although variables extracted by the support vector machine predicted donation behaviour well in the training sample ( N = 984), virtually, no variables from any method significantly predicted donations in a holdout sample ( N = 496). Raters’ attempts to predict donations to charity based on reading participants’ personal strivings were also unsuccessful. However, raters’ predictions were associated with past charitable involvement. In sum, predictors derived from personal strivings did not robustly explain variation in charitable behaviour, but personal strivings may nevertheless contain some information about trait prosociality. The sparseness of personal strivings data, rather than the irrelevance of open–ended text or individual differences in goal pursuit, likely explains their limited value in predicting prosocial behaviour. © 2020 European Association of Personality Psychology

Medical Image Classification Using an Optimal Feature Extraction Algorithm and a Supervised Classifier Technique

2011 ◽  
Vol 3 (2) ◽  
pp. 19-33 ◽  
Author(s):  
Ahmed Kharrat ◽  
Karim Gasmi ◽  
Mohamed Ben Messaoud ◽  
Nacéra Benamrane ◽  
Mohamed Abid
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Research Work ◽  
Reduction Rate ◽  
Support Vector ◽  
Forward Selection ◽  
Classification Rate ◽  
Brain Images ◽  
Input Module ◽  
Mr Brain Images

A new approach for automated diagnosis and classification of Magnetic Resonance (MR) human brain images is proposed. The proposed method uses Wavelets Transform (WT) as input module to Genetic Algorithm (GA) and Support Vector Machine (SVM). It segregates MR brain images into normal and abnormal. This contribution employs genetic algorithm for feature selection which requires much lighter computational burden in comparison with Sequential Floating Backward Selection (SFBS) and Sequential Floating Forward Selection (SFFS) methods. A percentage reduction rate of 88.63% is achieved. An excellent classification rate of 100% could be achieved using the support vector machine. The observed results are significantly better than the results reported in a previous research work employing Wavelet Transform and Support Vector Machine.

Coke Rate Prediction Model Based on Genetic Algorithm Optimized Support Vector Machine

2015 ◽  
Vol 740 ◽  
pp. 600-603
Author(s):  
You Jun Yue ◽  
Yan Fei Hu ◽  
Hui Zhao ◽  
Hong Jun Wang
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Absolute Error ◽  
Support Vector ◽  
Model Parameters ◽  
Coke Rate ◽  
Rate Model ◽  
Iron And Steel ◽  
Model Based ◽  
Blast Furnace Coke

The accurate prediction model’s establishing of the blast furnace coke rate is important for optimizing the integrated production indicators of iron and steel enterprise. For the problem of accuracy of the model of coke rate, This paper established blast coke rate modeling with support vector machine algorithm, the model parameters of support vector machine was optimized by genetic algorithm, then a coke rate model based on support vector machine with the best parameters was built. Simulation results showed that: the forecasting model’s outcome, average absolute error and the mean relative error, was small which is based on genetic algorithm optimized SVM. coke rate model based on Genetic algorithm optimized support vector machine has high degree of accuracy and a certain practicality.

Application of Support Vector Machine Modeling on Phase Distribution in the Riser of an LSCFB Reactor

2014 ◽  
Vol 12 (1) ◽  
pp. 123-134 ◽  
Author(s):  
Shaikh A. Razzak ◽  
Muhammad I. Hossain ◽  
Syed M. Rahman ◽  
Mohammad M. Hossain
Keyword(s):  
Support Vector Machine ◽  
Circulating Fluidized Bed ◽  
Phase Distribution ◽  
Solid Phase ◽  
Correlation Coefficients ◽  
Absolute Error ◽  
Pilot Scale ◽  
Support Vector ◽  
Cross Sectional ◽  
Machine Modeling

Abstract Support vector machine (SVM) modeling approach is applied to predict the solids holdups distribution of a liquid–solid circulating fluidized bed (LSCFB) riser. The SVM model is developed/trained using experimental data collected from a pilot-scale LSCFB reactor. Two different size glass bead particles (500 μm (GB-500) and 1,290 μm (GB-1290)) are used as solid phase, and water is used as liquid phase. The trained model successfully predicted the experimental solids holdups of the LSCFB riser under different operating parameters. It is observed that the model predicted cross-sectional average of solids holdups in the axial directions and radial flow structure are well agreement with the experimental values. The goodness of the model prediction is verified by using different statistical performance indicators. For the both sizes of particles, the mean absolute error is found to be less than 5%. The correlation coefficients (0.998 for GB-500 and 0.994 for GB-1290) also show favorable indications of the suitability of SVM approach in predicting the solids holdup of the LSCFB system.

Application of Independent Component Analysis in Short-Term Power Forecasting of Wind Farm

2011 ◽  
Vol 63-64 ◽  
pp. 124-128
Author(s):  
Guo Chu Chen ◽  
Peng Wang ◽  
Jin Shou Yu
Keyword(s):  
Support Vector Machine ◽  
Independent Component Analysis ◽  
Least Squares ◽  
Wind Farm ◽  
Absolute Error ◽  
Component Analysis ◽  
Independent Component ◽  
Support Vector ◽  
Number Of Factors ◽  
Power Forecasting

For the difficult problems of measuring and forecasting values interfered by a number of factors, this paper proposed a method of power forecasting based on independent component analysis and least squares support vector machine, and results are modified using the regression. Each independent component from source signals is predicted using least squares support vector machine, the final prediction results obtained by modifying the preliminary predicting power according to the relationship between wind speed and its power. Using the data from a wind farm on the Northeast China wind farm, the simulation results show that this method has higher prediction accuracy, and the mean absolute error from 9.25% down to 5.48%, compared with the simple least squares support vector machine models.

scholarly journals Support Vector Machine to Predict Electricity Consumption in the Energy Management Laboratory

2021 ◽  
Vol 5 (3) ◽  
pp. 466-473
Author(s):  
Azam Zamhuri Fuadi ◽  
Irsyad Nashirul Haq ◽  
Edi Leksono
Keyword(s):  
Support Vector Machine ◽  
Energy Management ◽  
Mean Squared Error ◽  
Measurement Data ◽  
Electricity Consumption ◽  
Absolute Error ◽  
Support Vector ◽  
Mean Error ◽  
Squared Error ◽  
Electrical Loads

Predicted electricity consumption is needed to perform energy management. Electricity consumption prediction is also very important in the development of intelligent power grids and advanced electrification network information. we implement a Support Vector Machine (SVM) to predict electrical loads and results compared to measurable electrical loads. Laboratory electrical loads have their own characteristics when compared to residential, commercial, or industrial, we use electrical load data in energy management laboratories to be used to be predicted. C and Gamma as searchable parameters use GridSearchCV to get optimal SVM input parameters. Our prediction data is compared to measurement data and is searched for accuracy based on RMSE (Root Square Mean Error), MAE (Mean Absolute Error) and MSE (Mean Squared Error) values. Based on this we get the optimal parameter values C 1e6 and Gamma 2.97e-07, with the result RSME (Root Square Mean Error) ; 0.37, MAE (meaning absolute error); 0.21 and MSE (Mean Squared Error); 0.14.

scholarly journals Design and analysis of an efficient machine learning based hybrid recommendation system with enhanced density-based spatial clustering for digital e-learning applications

2021 ◽  
Author(s):  
S. Bhaskaran ◽  
Raja Marappan
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Decision Making ◽  
Support Vector Machine ◽  
Absolute Error ◽  
Support Vector ◽  
E Learning ◽  
Public Datasets ◽  
Hybrid Recommender ◽  
New Strategies

AbstractA decision-making system is one of the most important tools in data mining. The data mining field has become a forum where it is necessary to utilize users' interactions, decision-making processes and overall experience. Nowadays, e-learning is indeed a progressive method to provide online education in long-lasting terms, contrasting to the customary head-to-head process of educating with culture. Through e-learning, an ever-increasing number of learners have profited from different programs. Notwithstanding, the highly assorted variety of the students on the internet presents new difficulties to the conservative one-estimate fit-all learning systems, in which a solitary arrangement of learning assets is specified to the learners. The problems and limitations in well-known recommender systems are much variations in the expected absolute error, consuming more query processing time, and providing less accuracy in the final recommendation. The main objectives of this research are the design and analysis of a new transductive support vector machine-based hybrid personalized hybrid recommender for the machine learning public data sets. The learning experience has been achieved through the habits of the learners. This research designs some of the new strategies that are experimented with to improve the performance of a hybrid recommender. The modified one-source denoising approach is designed to preprocess the learner dataset. The modified anarchic society optimization strategy is designed to improve the performance measurements. The enhanced and generalized sequential pattern strategy is proposed to mine the sequential pattern of learners. The enhanced transductive support vector machine is developed to evaluate the extracted habits and interests. These new strategies analyze the confidential rate of learners and provide the best recommendation to the learners. The proposed generalized model is simulated on public datasets for machine learning such as movies, music, books, food, merchandise, healthcare, dating, scholarly paper, and open university learning recommendation. The experimental analysis concludes that the enhanced clustering strategy discovers clusters that are based on random size. The proposed recommendation strategies achieve better significant performance over the methods in terms of expected absolute error, accuracy, ranking score, recall, and precision measurements. The accuracy of the proposed datasets lies between 82 and 98%. The MAE metric lies between 5 and 19.2% for the simulated public datasets. The simulation results prove the proposed generalized recommender has a great strength to improve the quality and performance.

Sign in / Sign up

Export Citation Format

Share Document