11,880 Hits in 4.6 sec

Explicability in resting-state fMRI for gender classification

Adrien Raison, Pascal Bourdon, Christophe Habas, David Helbert
2021 2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME)  
Artificial Intelligence, especially deep neural networks, have shown impressive performances for classification tasks since the last decade.  ...  In this study we propose to leverage the power of deep neural network for classifying resting state brain activities by gender, then we use explainable Artificial Intelligence models to determine which  ...  Procedure Classification task Independent component analysis (ICA) generates statistically mutually independent spatial maps whose (neural) nodes display synchronized spontaneous BOLD fluctuations during  ... 
doi:10.1109/icabme53305.2021.9604842 fatcat:s52ijald2rh5lft7wkq44s5tim

Modeling Course Achievements of Elementary Education Teacher Candidates with Artificial Neural Networks

Ergün Akgün, Metin Demir
2018 International Journal of Assessment Tools in Education  
Acknowledgements This research was produced from doctoral thesis titled "Modeling of Science and Technology Teaching Course Achievements of Elementary Teacher Candidates with Artificial Neural Networks  ...  Although the components forming an artificial neural network are mainly composed of these components, artificial neural networks vary in many different classifications according to their intended use.  ...  Weights used in artificial neural networks fulfill the function of synapses, while the axons represent the neuronal output of the artificial neural network.  ... 
doi:10.21449/ijate.444073 fatcat:p6at7sbrx5h37mt44tv36jodfa

Novel Classification of Ischemic Heart Disease Using Artificial Neural Network [article]

Giulia Silveri, Marco Merlo, Luca Restivo, Gianfranco Sinagra, Agostino Accardo
2020 arXiv   pre-print
However, so far, IHD patients were identified using Artificial Neural Networks (ANNs) applied to a limited number of HRV parameters and only to very few subjects.  ...  By using principal component analysis and stepwise regression, we reduced the original 17 parameters to five, used as inputs, for a series of ANNs.  ...  However, even if some authors developed cardiovascular disease classification systems based on artificial neural network using few of parameters extracted from HRV [7] [8] [9] and some clinical features  ... 
arXiv:2011.09801v1 fatcat:5ri7gq3tnnedxbcxhfnlvecury

Gender Classification using Distance Classifier and Neural Network

Ms. Sushree Silpika Pattanayak, Ms. Sunita Dalai, Sujit Kumar Jena
2015 International Journal of Engineering Research and  
A radial basis function network is an artificial neural network that uses radial basis functions as activation functions.  ...  So far detection of gender using facial features is done by using the methods like Distance classifier and neural network.  ...  of an image Fig. 4 4 ZigZag Algorithm for Feature selection B .Gender Classification Using RBFN Fig.5 Flow Diagram of Neural Network Classifier method 1) Feature Extraction: Here we have used 2D Discrete  ... 
doi:10.17577/ijertv4is040371 fatcat:fsvnb7gqnrasppezgf3wtbknea

1-D convolutional neural network based on the inner ear principle to automatically assess human's emotional state

A.O. Iskhakova, D.A. Wolf, R.R. Galin, M.V. Mamchenko, V. Breskich, A. Zheltenkov, Y. Dreizis
2020 E3S Web of Conferences  
The article proposes an original convolutional neural network (CNN) for solving the problem of the automatic voice-based assessment of a person's emotional state.  ...  According to the given classification estimates, the proposed CNN model is regarded to be not worse than the known analogues.  ...  features extracted from the speech signal according to the general model of the Artificial Neural Network [16, 17] using an acoustic characteristic based on the MFCC.  ... 
doi:10.1051/e3sconf/202022401023 fatcat:g4yrlxqppza2hgoovkthafvohu


Ömer Faruk RENÇBER, Sinan METE
2018 Business And Management Studies An International Journal  
This study aims to make a comparison between the classification performances of artificial neural network (ANN) from machine learning techniques and Adaptive Neural Fuzzy Inference System (ANFIS), which  ...  For this purpose, besides multivariate statistical techniques, methods based on fuzzy and artificial intelligence are also used today.  ...  A neural network model was given as an example in Figure 1 . Figure 1. Artificial Neural Network Model An artificial neural network comprises five main components.  ... 
doi:10.15295/bmij.v6i3.356 fatcat:yz3tlgcqhjbsto4qyd2wfvm3aa

Neuromarketing Solutions based on EEG Signal Analysis using Machine Learning

Asad Ullah, Gulsher Baloch, Ahmed Ali, Abdul Baseer Buriro, Junaid Ahmed, Bilal Ahmed, Saba Akhtar
2022 International Journal of Advanced Computer Science and Applications  
classification using a user-independent testing method.  ...  Furthermore, the results of product-wise classification were relatively higher with 81.23 percent using Artificial Neural Networks and 80.38 percent using Support Vector Machine.  ...  Artificial Neural Networks.  ... 
doi:10.14569/ijacsa.2022.0130137 fatcat:kqrqiinkobda7mvgydbesyfgoi


T Jemima Jebaseeli
This model is used for predicting the outcome. Deep learning is a subset of machine learning which is inspired on function of a brain with artificial neural networks [I].  ...  The proposed network is created using tensor flow and image processing is done using opencv. Tensor flow is used to setup, train and deploy neural network with large dataset.  ...  Classification requires training the network with a dataset. Training is done using an artificial neural network which is similar to the neural system in the human brain.  ... 
doi:10.26782/jmcms.2020.02.00010 fatcat:fwkjbrzownep7a6wbs236lreia

The Use of Neural Networks to Predict the Number of Gifted Students

2021 International Journal on Humanities and Social Sciences  
descriptive method of the pattern of the Artificial Neural Networks.  ...  Perception network. 1 Definition of Artificial Neural Networks (ANN): The ANN is a pattern that resembles the natural biological network & uses a number of basic ways used in natural neurologic  ... 
doi:10.33193/ijohss.22.2021.265 fatcat:lpxu2v6oarejjbwwuryfllfssi

Neural Contrastive Clustering: Fully Unsupervised Bias Reduction for Sentiment Classification [article]

Jared Mowery
2022 arXiv   pre-print
This discourages the neural network from learning topic-related features that produce biased classification results.  ...  Neural networks produce biased classification results due to correlation bias (they learn correlations between their inputs and outputs to classify samples, even when those correlations do not represent  ...  Dropout regularization [34] is used in all three components of the neural network.  ... 
arXiv:2204.10467v1 fatcat:eblsafmg55czrhihy63sk4j27a

Study of a Machine Learning Model for Face Detection, Age Detection, and Gender Recognition

Aditya Sinha
2020 International Journal for Research in Applied Science and Engineering Technology  
Machine learning offers different models for age and gender recognition such as convolutional neural networks, feed forward neural network, and recurrent neural network.  ...  In our review we will be describing our system that takes input from the user and gives age and gender as output. User can provide input through browsing an image or through web camera.  ...  For prediction of age and gender artificial neural network is used, namely -Convolutional neural network, Rectified linear unit layers and Pooling layers.  ... 
doi:10.22214/ijraset.2020.5007 fatcat:cdvn2wy2kbaj3ickiv522mfczq

Deep-Learning-Based Adaptive Advertising with Augmented Reality

Marco A. Moreno-Armendáriz, Hiram Calvo, Carlos A. Duchanoy, Arturo Lara-Cázares, Enrique Ramos-Diaz, Víctor L. Morales-Flores
2021 Sensors  
In order to present suitable digital posters for each person, several technologies were used: Augmented reality, estimation of age, gender, and estimation of personality through the Big Five test applied  ...  In this work we describe a system composed of deep neural networks that analyzes characteristics of customers based on their face (age, gender, and personality), as well as the ambient temperature, with  ...  To achieve the objective, artificial vision techniques will be used from cameras strategically installed in the premises, together with neural networks that will allow estimating the age, gender, and personality  ... 
doi:10.3390/s22010063 pmid:35009606 pmcid:PMC8747126 fatcat:hzxax2vv25fotix22vlmogtn7i

Sample Reduction for Physiological Data Analysis Using Principal Component Analysis in Artificial Neural Network

Cid Mathew Santiago Adolfo, Hassan Chizari, Thu Yein Win, Salah Al-Majeed
2021 Applied Sciences  
Removing noisy samples in dirty datasets is integral to and crucial in biomedical applications, such as the classification and prediction problems using artificial neural networks (ANNs) in the body's  ...  In this study, we developed a methodology to identify and remove noisy data from a dataset before addressing the classification problem of an artificial neural network (ANN) by proposing the use of the  ...  When it applies to the classification problem of an artificial neural network (ANN), obtaining the correct values through comprehensive and extensive quantisation in data-signal processing is essential  ... 
doi:10.3390/app11178240 fatcat:unf6jlom5vh7dg73no5axn3ghq

Neural Network in Developing Software for Indentifying Arch Form

Johan Arief Budiman
2013 International Journal of Artificial Intelligence & Applications  
A software using artificial neural network to describe arch form qualitatively could be used for diagnostic reference to Class I malocclusion orthodontic post treatment.  ...  The objective of this study is to develop qualitative arch form diagnostic references using artificial neural network from pre-post treatment dental cast scanning result.  ...  Artificial neural networks worked in the same manner as biologic neural networks do.  ... 
doi:10.5121/ijaia.2013.4301 fatcat:b42akjt3hneylflp7orf6d4rqq

Credit Risk of Bank Customers can be Predicted from Customer's Attribute using Neural Network

Subrata Saha, Sajjad Waheed
2017 International Journal of Computer Applications  
Artificial neural network is used for loan applicants' credit risk measurement and the calculations have been done by using SPSS and WEKA software.  ...  The aim of this paper is to present a model based on Multilayer perceptron neural networks to recognize bad or good credit customers. Credit risk is one of the major problems in banking sector.  ...  A neural network consists of an interconnected group of artificial neurons, and it processes information using a connectionist approach to computation.  ... 
doi:10.5120/ijca2017913170 fatcat:tamqyb4ifvdqjo4wqtgcpysr4u
« Previous Showing results 1 — 15 out of 11,880 results