Search Results for author: Seyed Mostafa Kia

Found 12 papers, 3 papers with code

PROMISSING: Pruning Missing Values in Neural Networks

no code implementations3 Jun 2022 Seyed Mostafa Kia, Nastaran Mohammadian Rad, Daniel van Opstal, Bart van Schie, Andre F. Marquand, Josien Pluim, Wiepke Cahn, Hugo G. Schnack

In this method, there is no need to remove or impute the missing values; instead, the missing values are treated as a new source of information (representing what we do not know).

BIG-bench Machine Learning Imputation

Hierarchical Bayesian Regression for Multi-Site Normative Modeling of Neuroimaging Data

1 code implementation25 May 2020 Seyed Mostafa Kia, Hester Huijsdens, Richard Dinga, Thomas Wolfers, Maarten Mennes, Ole A. Andreassen, Lars T. Westlye, Christian F. Beckmann, Andre F. Marquand

Clinical neuroimaging has recently witnessed explosive growth in data availability which brings studying heterogeneity in clinical cohorts to the spotlight.

regression

Neural Processes Mixed-Effect Models for Deep Normative Modeling of Clinical Neuroimaging Data

1 code implementation12 Dec 2018 Seyed Mostafa Kia, Andre F. Marquand

Normative modeling has recently been introduced as a promising approach for modeling variation of neuroimaging measures across individuals in order to derive biomarkers of psychiatric disorders.

Novelty Detection regression

Scalable Multi-Task Gaussian Process Tensor Regression for Normative Modeling of Structured Variation in Neuroimaging Data

no code implementations31 Jul 2018 Seyed Mostafa Kia, Christian F. Beckmann, Andre F. Marquand

Most brain disorders are very heterogeneous in terms of their underlying biology and developing analysis methods to model such heterogeneity is a major challenge.

Anomaly Detection Multi-Task Learning

Normative Modeling of Neuroimaging Data using Scalable Multi-Task Gaussian Processes

no code implementations4 Jun 2018 Seyed Mostafa Kia, Andre Marquand

Normative modeling has recently been proposed as an alternative for the case-control approach in modeling heterogeneity within clinical cohorts.

Gaussian Processes Novelty Detection +1

Deep Learning for Automatic Stereotypical Motor Movement Detection using Wearable Sensors in Autism Spectrum Disorders

no code implementations14 Sep 2017 Nastaran Mohammadian Rad, Seyed Mostafa Kia, Calogero Zarbo, Twan van Laarhoven, Giuseppe Jurman, Paola Venuti, Elena Marchiori, Cesare Furlanello

Our results show that: 1) feature learning outperforms handcrafted features; 2) parameter transfer learning is beneficial in longitudinal settings; 3) using LSTM to learn the temporal dynamic of signals enhances the detection rate especially for skewed training data; 4) an ensemble of LSTMs provides more accurate and stable detectors.

Ensemble Learning Transfer Learning

Interpretability in Linear Brain Decoding

no code implementations17 Jun 2016 Seyed Mostafa Kia, Andrea Passerini

Despite extensive studies of this type, at present, there is no formal definition for interpretability of brain decoding models.

Brain Decoding Model Selection

Interpretability of Multivariate Brain Maps in Brain Decoding: Definition and Quantification

1 code implementation29 Mar 2016 Seyed Mostafa Kia

In this paper, first, we present a theoretical definition of interpretability in brain decoding; we show that the interpretability of multivariate brain maps can be decomposed into their reproducibility and representativeness.

Brain Decoding Model Selection +1

Convolutional Neural Network for Stereotypical Motor Movement Detection in Autism

no code implementations5 Nov 2015 Nastaran Mohammadian Rad, Andrea Bizzego, Seyed Mostafa Kia, Giuseppe Jurman, Paola Venuti, Cesare Furlanello

Autism Spectrum Disorders (ASDs) are often associated with specific atypical postural or motor behaviors, of which Stereotypical Motor Movements (SMMs) have a specific visibility.

Transfer Learning valid

Mass-Univariate Hypothesis Testing on MEEG Data using Cross-Validation

no code implementations25 Jun 2014 Seyed Mostafa Kia

Recent advances in statistical theory, together with advances in the computational power of computers, provide alternative methods to do mass-univariate hypothesis testing in which a large number of univariate tests, can be properly used to compare MEEG data at a large number of time-frequency points and scalp locations.

Two-sample testing

MEG Decoding Across Subjects

no code implementations16 Apr 2014 Emanuele Olivetti, Seyed Mostafa Kia, Paolo Avesani

On a face vs. scramble task MEG dataset of 16 subjects, we compare the standard approach of not modelling the differences across subjects, to the proposed one of combining TTL and ensemble learning.

Brain Decoding Ensemble Learning +1

A Novel Scheme for Intelligent Recognition of Pornographic Images

no code implementations24 Feb 2014 Seyed Mostafa Kia, Hossein Rahmani, Reza Mortezaei, Mohsen Ebrahimi Moghaddam, Amer Namazi

To test the proposed method, performance of system was evaluated over 18354 download images from internet.

Cannot find the paper you are looking for? You can Submit a new open access paper.