Search Results for author: Moncef Gabbouj

Found 103 papers, 26 papers with code

A Personalized Zero-Shot ECG Arrhythmia Monitoring System: From Sparse Representation Based Domain Adaption to Energy Efficient Abnormal Beat Detection for Practical ECG Surveillance

1 code implementation14 Jul 2022 Mehmet Yamaç, Mert Duman, İlke Adalıoğlu, Serkan Kiranyaz, Moncef Gabbouj

An extensive set of experiments performed on the benchmark MIT-BIH ECG dataset shows that when this domain adaptation-based training data generator is used with a simple 1-D CNN classifier, the method outperforms the prior work by a significant margin.

Arrhythmia Detection Dictionary Learning +4

Early Myocardial Infarction Detection with One-Class Classification over Multi-view Echocardiography

no code implementations14 Apr 2022 Aysen Degerli, Fahad Sohrab, Serkan Kiranyaz, Moncef Gabbouj

In this study, we propose a framework for early detection of MI over multi-view echocardiography that leverages one-class classification (OCC) techniques.

Classification Myocardial infarction detection

Global ECG Classification by Self-Operational Neural Networks with Feature Injection

no code implementations7 Apr 2022 Muhammad Uzair Zahid, Serkan Kiranyaz, Moncef Gabbouj

The classification layers can thus benefit from both temporal and learned features for the final arrhythmia classification.

Arrhythmia Detection Classification +1

OSegNet: Operational Segmentation Network for COVID-19 Detection using Chest X-ray Images

no code implementations21 Feb 2022 Aysen Degerli, Serkan Kiranyaz, Muhammad E. H. Chowdhury, Moncef Gabbouj

To address the data scarcity encountered in training and especially in evaluation, this study extends the largest COVID-19 CXR dataset: QaTa-COV19 with 121, 378 CXRs including 9258 COVID-19 samples with their corresponding ground-truth segmentation masks that are publicly shared with the research community.

SRL-SOA: Self-Representation Learning with Sparse 1D-Operational Autoencoder for Hyperspectral Image Band Selection

1 code implementation20 Feb 2022 Mete Ahishali, Serkan Kiranyaz, Iftikhar Ahmad, Moncef Gabbouj

The band selection in the hyperspectral image (HSI) data processing is an important task considering its effect on the computational complexity and accuracy.

Representation Learning

Non-Linear Spectral Dimensionality Reduction Under Uncertainty

no code implementations9 Feb 2022 Firas Laakom, Jenni Raitoharju, Nikolaos Passalis, Alexandros Iosifidis, Moncef Gabbouj

In this paper, we consider the problem of non-linear dimensionality reduction under uncertainty, both from a theoretical and algorithmic perspectives.

Dimensionality Reduction

Reducing Redundancy in the Bottleneck Representation of the Autoencoders

no code implementations9 Feb 2022 Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.

Dimensionality Reduction Image Compression +1

Blind ECG Restoration by Operational Cycle-GANs

1 code implementation29 Jan 2022 Serkan Kiranyaz, Ozer Can Devecioglu, Turker Ince, Junaid Malik, Muhammad Chowdhury, Tahir Hamid, Rashid Mazhar, Amith Khandakar, Anas Tahir, Tawsifur Rahman, Moncef Gabbouj

Usually, a set of such artifacts occur on the same ECG signal with varying severity and duration, and this makes an accurate diagnosis by machines or medical doctors extremely difficult.

Denoising ECG Denoising

Self-attention fusion for audiovisual emotion recognition with incomplete data

1 code implementation26 Jan 2022 Kateryna Chumachenko, Alexandros Iosifidis, Moncef Gabbouj

In this paper, we consider the problem of multimodal data analysis with a use case of audiovisual emotion recognition.

Facial Emotion Recognition

Self-Attention Neural Bag-of-Features

no code implementations26 Jan 2022 Kateryna Chumachenko, Alexandros Iosifidis, Moncef Gabbouj

In this work, we propose several attention formulations for multivariate sequence data.

Image denoising by Super Neurons: Why go deep?

no code implementations29 Nov 2021 Junaid Malik, Serkan Kiranyaz, Moncef Gabbouj

As the integration of non-local information is known to benefit denoising, in this work we investigate the use of super neurons for both synthetic and real-world image denoising.

Image Denoising

Robust channel-wise illumination estimation

1 code implementation10 Nov 2021 Firas Laakom, Jenni Raitoharju, Jarno Nikkanen, Alexandros Iosifidis, Moncef Gabbouj

We test this approach on the proposed method and show that it can indeed be used to avoid several extreme error cases and, thus, improves the practicality of the proposed technique.

Color Constancy

Learning to ignore: rethinking attention in CNNs

1 code implementation10 Nov 2021 Firas Laakom, Kateryna Chumachenko, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

Based on this idea, we propose to reformulate the attention mechanism in CNNs to learn to ignore instead of learning to attend.

Early Myocardial Infarction Detection over Multi-view Echocardiography

no code implementations9 Nov 2021 Aysen Degerli, Serkan Kiranyaz, Tahir Hamid, Rashid Mazhar, Moncef Gabbouj

Myocardial infarction (MI) is the leading cause of mortality in the world that occurs due to a blockage of the coronary arteries feeding the myocardium.

Myocardial infarction detection

Early Bearing Fault Diagnosis of Rotating Machinery by 1D Self-Organized Operational Neural Networks

no code implementations30 Sep 2021 Turker Ince, Junaid Malik, Ozer Can Devecioglu, Serkan Kiranyaz, Onur Avci, Levent Eren, Moncef Gabbouj

Preventive maintenance of modern electric rotating machinery (RM) is critical for ensuring reliable operation, preventing unpredicted breakdowns and avoiding costly repairs.

Robust Peak Detection for Holter ECGs by Self-Organized Operational Neural Networks

no code implementations30 Sep 2021 Serkan Kiranyaz, Junaid Malik, Muhammad Uzair Zahid, Turker Ince, Muhammad Chowdhury, Amith Khandakar, Anas Tahir, Moncef Gabbouj

This has been addressed by Operational Neural Networks (ONNs) with their heterogenous network configuration encapsulating neurons with various non-linear operators.

Real-Time Patient-Specific ECG Classification by 1D Self-Operational Neural Networks

no code implementations30 Sep 2021 Junaid Malik, Ozer Can Devecioglu, Serkan Kiranyaz, Turker Ince, Moncef Gabbouj

Despite the proliferation of numerous deep learning methods proposed for generic ECG classification and arrhythmia detection, compact systems with the real-time ability and high accuracy for classifying patient-specific ECG are still few.

Arrhythmia Detection Classification +1

Improving Neural Network Generalization via Promoting Within-Layer Diversity

no code implementations29 Sep 2021 Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

Neural networks are composed of multiple layers arranged in a hierarchical structure jointly trained with a gradient-based optimization, where the errors are back-propagated from the last layer back to the first one.

Real-Time Glaucoma Detection from Digital Fundus Images using Self-ONNs

no code implementations28 Sep 2021 Ozer Can Devecioglu, Junaid Malik, Turker Ince, Serkan Kiranyaz, Eray Atalay, Moncef Gabbouj

Glaucoma leads to permanent vision disability by damaging the optical nerve that transmits visual images to the brain.

Remote Multilinear Compressive Learning with Adaptive Compression

no code implementations2 Sep 2021 Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis

By developing compressive sensing and learning models that can operate with an adaptive compression rate, we can maximize the informational content throughput of the whole application.

Compressive Sensing

Bilinear Input Normalization for Neural Networks in Financial Forecasting

no code implementations1 Sep 2021 Dat Thanh Tran, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis

Data normalization is one of the most important preprocessing steps when building a machine learning model, especially when the model of interest is a deep neural network.

Time Series

Generalized Tensor Summation Compressive Sensing Network (GTSNET): An Easy to Learn Compressive Sensing Operation

no code implementations4 Aug 2021 Mehmet Yamac, Ugur Akpinar, Erdem Sahin, Serkan Kiranyaz, Moncef Gabbouj

For a special case where the CS operation is set as a single tensor multiplication, the model is reduced to the learning-based separable CS; while a dense CS matrix can be approximated and learned as the summation of multiple tensors.

Compressive Sensing

Super Neurons

no code implementations3 Aug 2021 Serkan Kiranyaz, Junaid Malik, Mehmet Yamac, Esin Guldogan, Turker Ince, Moncef Gabbouj

The idea behind the "generative neurons" was born as a remedy for this restriction where each nodal operator can be "customized" during the training in order to maximize the learning performance.

Representation Based Regression for Object Distance Estimation

2 code implementations27 Jun 2021 Mete Ahishali, Mehmet Yamac, Serkan Kiranyaz, Moncef Gabbouj

To the best of our knowledge, this is the first representation-based method proposed for performing a regression task by utilizing the modified CSENs; and hence, we name this novel approach as Representation-based Regression (RbR).

3D Object Detection object-detection

Learning distinct features helps, provably

no code implementations10 Jun 2021 Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

We study the diversity of the features learned by a two-layer neural network trained with the least squares loss.

Generalization Bounds

AnomalyHop: An SSL-based Image Anomaly Localization Method

1 code implementation8 May 2021 Kaitai Zhang, Bin Wang, Wei Wang, Fahad Sohrab, Moncef Gabbouj, C. -C. Jay Kuo

An image anomaly localization method based on the successive subspace learning (SSL) framework, called AnomalyHop, is proposed in this work.

Knowledge Distillation By Sparse Representation Matching

1 code implementation31 Mar 2021 Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis

Knowledge Distillation refers to a class of methods that transfers the knowledge from a teacher network to a student network.

Knowledge Distillation Representation Learning

Convolutional versus Self-Organized Operational Neural Networks for Real-World Blind Image Denoising

1 code implementation4 Mar 2021 Junaid Malik, Serkan Kiranyaz, Mehmet Yamac, Esin Guldogan, Moncef Gabbouj

Real-world blind denoising poses a unique image restoration challenge due to the non-deterministic nature of the underlying noise distribution.

Image Denoising Image Restoration

BM3D vs 2-Layer ONN

no code implementations4 Mar 2021 Junaid Malik, Serkan Kiranyaz, Mehmet Yamac, Moncef Gabbouj

Despite their recent success on image denoising, the need for deep and complex architectures still hinders the practical usage of CNNs.

Image Denoising

On Feature Diversity in Energy-based models

no code implementations ICLR Workshop EBM 2021 Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches.

Generalization Bounds

Ensembling object detectors for image and video data analysis

no code implementations9 Feb 2021 Kateryna Chumachenko, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

In this paper, we propose a method for ensembling the outputs of multiple object detectors for improving detection performance and precision of bounding boxes on image data.

object-detection Object Detection

Reliable COVID-19 Detection Using Chest X-ray Images

no code implementations28 Jan 2021 Aysen Degerli, Mete Ahishali, Serkan Kiranyaz, Muhammad E. H. Chowdhury, Moncef Gabbouj

To address this need, in this study, we propose a reliable COVID-19 detection network: ReCovNet, which can discriminate COVID-19 pneumonia from 14 different thoracic diseases and healthy subjects.

COVID-19 Diagnosis

ON NEURAL NETWORK GENERALIZATION VIA PROMOTING WITHIN-LAYER ACTIVATION DIVERSITY

no code implementations1 Jan 2021 Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

During the last decade, neural networks have been intensively used to tackle various problems and they have often led to state-of-the-art results.

Robust R-Peak Detection in Low-Quality Holter ECGs using 1D Convolutional Neural Network

no code implementations29 Dec 2020 Muhammad Uzair Zahid, Serkan Kiranyaz, Turker Ince, Ozer Can Devecioglu, Muhammad E. H. Chowdhury, Amith Khandakar, Anas Tahir, Moncef Gabbouj

Results also demonstrate similar or better performance than most competing algorithms on MIT-DB with 99. 83% F1-score, 99. 85% recall, and 99. 82% precision.

Classification of Polarimetric SAR Images Using Compact Convolutional Neural Networks

no code implementations10 Nov 2020 Mete Ahishali, Serkan Kiranyaz, Turker Ince, Moncef Gabbouj

In this work, to address the limitations of traditional ML and deep CNN based methods, a novel and systematic classification framework is proposed for the classification of PolSAR images, based on a compact and adaptive implementation of CNNs using a sliding-window classification approach.

Classification General Classification

Early Detection of Myocardial Infarction in Low-Quality Echocardiography

no code implementations5 Oct 2020 Aysen Degerli, Morteza Zabihi, Serkan Kiranyaz, Tahir Hamid, Rashid Mazhar, Ridha Hamila, Moncef Gabbouj

Myocardial infarction (MI), or commonly known as heart attack, is a life-threatening health problem worldwide from which 32. 4 million people suffer each year.

Feature Engineering

COVID-19 Infection Map Generation and Detection from Chest X-Ray Images

no code implementations26 Sep 2020 Aysen Degerli, Mete Ahishali, Mehmet Yamac, Serkan Kiranyaz, Muhammad E. H. Chowdhury, Khalid Hameed, Tahir Hamid, Rashid Mazhar, Moncef Gabbouj

To accomplish this, we have compiled the largest dataset with 119, 316 CXR images including 2951 COVID-19 samples, where the annotation of the ground-truth segmentation masks is performed on CXRs by a novel collaborative human-machine approach.

COVID-19 Diagnosis

Performance Indicator in Multilinear Compressive Learning

no code implementations22 Sep 2020 Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis

Recently, the Multilinear Compressive Learning (MCL) framework was proposed to efficiently optimize the sensing and learning steps when working with multidimensional signals, i. e. tensors.

Compressive Sensing

Graph Embedding with Data Uncertainty

no code implementations1 Sep 2020 Firas Laakom, Jenni Raitoharju, Nikolaos Passalis, Alexandros Iosifidis, Moncef Gabbouj

spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines.

Graph Embedding

Operational vs Convolutional Neural Networks for Image Denoising

no code implementations1 Sep 2020 Junaid Malik, Serkan Kiranyaz, Moncef Gabbouj

Convolutional Neural Networks (CNNs) have recently become a favored technique for image denoising due to its adaptive learning ability, especially with a deep configuration.

Image Denoising

Self-Organized Operational Neural Networks for Severe Image Restoration Problems

no code implementations29 Aug 2020 Junaid Malik, Serkan Kiranyaz, Moncef Gabbouj

Discriminative learning based on convolutional neural networks (CNNs) aims to perform image restoration by learning from training examples of noisy-clean image pairs.

Denoising Image Restoration

Exploiting Heterogeneity in Operational Neural Networks by Synaptic Plasticity

no code implementations21 Aug 2020 Serkan Kiranyaz, Junaid Malik, Habib Ben Abdallah, Turker Ince, Alexandros Iosifidis, Moncef Gabbouj

As a heterogenous network model, ONNs are based on a generalized neuron model that can encapsulate any set of non-linear operators to boost diversity and to learn highly complex and multi-modal functions or spaces with minimal network complexity and training data.

Learning Theory

Left Ventricular Wall Motion Estimation by Active Polynomials for Acute Myocardial Infarction Detection

no code implementations11 Aug 2020 Serkan Kiranyaz, Aysen Degerli, Tahir Hamid, Rashid Mazhar, Rayyan Ahmed, Rayaan Abouhasera, Morteza Zabihi, Junaid Malik, Ridha Hamila, Moncef Gabbouj

It further enables medical experts to gain an enhanced visualization capability of echo images through color-coded segments along with their "maximum motion displacement" plots helping them to better assess wall motion and LV Ejection-Fraction (LVEF).

Motion Estimation Myocardial infarction detection

Advance Warning Methodologies for COVID-19 using Chest X-Ray Images

1 code implementation7 Jun 2020 Mete Ahishali, Aysen Degerli, Mehmet Yamac, Serkan Kiranyaz, Muhammad E. H. Chowdhury, Khalid Hameed, Tahir Hamid, Rashid Mazhar, Moncef Gabbouj

The detection of COVID-19 in early stages is not a straightforward task from chest X-ray images according to expert medical doctors because the traces of the infection are visible only when the disease has progressed to a moderate or severe stage.

Transfer Learning

FastONN -- Python based open-source GPU implementation for Operational Neural Networks

1 code implementation3 Jun 2020 Junaid Malik, Serkan Kiranyaz, Moncef Gabbouj

Operational Neural Networks (ONNs) have recently been proposed as a special class of artificial neural networks for grid structured data.

Attention-based Neural Bag-of-Features Learning for Sequence Data

1 code implementation25 May 2020 Dat Thanh Tran, Nikolaos Passalis, Anastasios Tefas, Moncef Gabbouj, Alexandros Iosifidis

In this paper, we propose 2D-Attention (2DA), a generic attention formulation for sequence data, which acts as a complementary computation block that can detect and focus on relevant sources of information for the given learning objective.

Medical Diagnosis

Complexity Analysis Of Next-Generation VVC Encoding and Decoding

1 code implementation21 May 2020 Farhad Pakdaman, Mohammad Ali Adelimanesh, Moncef Gabbouj, Mahmoud Reza Hashemi

While the next generation video compression standard, Versatile Video Coding (VVC), provides a superior compression efficiency, its computational complexity dramatically increases.

Multimedia Computational Complexity Image and Video Processing

Probabilistic Color Constancy

no code implementations6 May 2020 Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Uygar Tuna, Jarno Nikkanen, Moncef Gabbouj

In this paper, we propose a novel unsupervised color constancy method, called Probabilistic Color Constancy (PCC).

Color Constancy

Self-Organized Operational Neural Networks with Generative Neurons

no code implementations24 Apr 2020 Serkan Kiranyaz, Junaid Malik, Habib Ben Abdallah, Turker Ince, Alexandros Iosifidis, Moncef Gabbouj

However, Greedy Iterative Search (GIS) method, which is the search method used to find optimal operators in ONNs takes many training sessions to find a single operator set per layer.

Saliency-based Weighted Multi-label Linear Discriminant Analysis

no code implementations8 Apr 2020 Lei Xu, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

The proposed method is based on a probabilistic model for defining the weights of individual samples in a weighted multi-label LDA approach.

Classification General Classification +1

Not all domains are equally complex: Adaptive Multi-Domain Learning

no code implementations25 Mar 2020 Ali Senhaji, Jenni Raitoharju, Moncef Gabbouj, Alexandros Iosifidis

The most common approach in multi-domain learning is to form a domain agnostic model, the parameters of which are shared among all domains, and learn a small number of extra domain-specific parameters for each individual new domain.

Ellipsoidal Subspace Support Vector Data Description

1 code implementation20 Mar 2020 Fahad Sohrab, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

In this paper, we propose a novel method for transforming data into a low-dimensional space optimized for one-class classification.

General Classification

Convolutional Sparse Support Estimator Network (CSEN) From energy efficient support estimation to learning-aided Compressive Sensing

no code implementations2 Mar 2020 Mehmet Yamac, Mete Ahishali, Serkan Kiranyaz, Moncef Gabbouj

Indeed, a vast majority of them use sparse signal recovery techniques to obtain support sets instead of directly mapping the non-zero locations from denser measurements (e. g., Compressively Sensed Measurements).

Compressive Sensing Face Recognition

Subset Sampling For Progressive Neural Network Learning

1 code implementation17 Feb 2020 Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis

Progressive Neural Network Learning is a class of algorithms that incrementally construct the network's topology and optimize its parameters based on the training data.

Face Recognition

Multilinear Compressive Learning with Prior Knowledge

1 code implementation17 Feb 2020 Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis

Extensive experiments demonstrate that the proposed knowledge transfer method can effectively train MCL models to compressively sense and synthesize better features for the learning tasks with improved performances, especially when the complexity of the learning task increases.

Compressive Sensing Transfer Learning

Incremental Fast Subclass Discriminant Analysis

no code implementations11 Feb 2020 Kateryna Chumachenko, Jenni Raitoharju, Moncef Gabbouj, Alexandros Iosifidis

This paper proposes an incremental solution to Fast Subclass Discriminant Analysis (fastSDA).

Neural Architecture Search by Estimation of Network Structure Distributions

no code implementations19 Aug 2019 Anton Muravev, Jenni Raitoharju, Moncef Gabbouj

Our matrix of probabilities is equivalent to the population of models, but allows for discovery of structural irregularities, while being simple to interpret and analyze.

Neural Architecture Search

Reversible Privacy Preservation using Multi-level Encryption and Compressive Sensing

no code implementations20 Jun 2019 Mehmet Yamac, Mete Ahishali, Nikolaos Passalis, Jenni Raitoharju, Bulent Sankur, Moncef Gabbouj

Security monitoring via ubiquitous cameras and their more extended in intelligent buildings stand to gain from advances in signal processing and machine learning.

Compressive Sensing De-identification +1

Bag of Color Features For Color Constancy

1 code implementation11 Jun 2019 Firas Laakom, Nikolaos Passalis, Jenni Raitoharju, Jarno Nikkanen, Anastasios Tefas, Alexandros Iosifidis, Moncef Gabbouj

To further improve the illumination estimation accuracy, we propose a novel attention mechanism for the BoCF model with two variants based on self-attention.

Color Constancy

Color Constancy Convolutional Autoencoder

no code implementations4 Jun 2019 Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Jarno Nikkanen, Moncef Gabbouj

In this paper, we study the importance of pre-training for the generalization capability in the color constancy problem.

Color Constancy Unsupervised Pre-training

Multilinear Compressive Learning

2 code implementations17 May 2019 Dat Thanh Tran, Mehmet Yamac, Aysen Degerli, Moncef Gabbouj, Alexandros Iosifidis

Compressive Learning is an emerging topic that combines signal acquisition via compressive sensing and machine learning to perform inference tasks directly on a small number of measurements.

Compressive Sensing Face Recognition

1D Convolutional Neural Networks and Applications: A Survey

no code implementations9 May 2019 Serkan Kiranyaz, Onur Avci, Osama Abdeljaber, Turker Ince, Moncef Gabbouj, Daniel J. Inman

During the last decade, Convolutional Neural Networks (CNNs) have become the de facto standard for various Computer Vision and Machine Learning operations.

Anomaly Detection Fault Detection

Speed-up and multi-view extensions to Subclass Discriminant Analysis

1 code implementation2 May 2019 Kateryna Chumachenko, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

We show that by exploiting the structure of the between-class Laplacian matrix, the eigendecomposition step can be substituted with a much faster process.

Graph Embedding

Multimodal Subspace Support Vector Data Description

1 code implementation16 Apr 2019 Fahad Sohrab, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

In this paper, we propose a novel method for projecting data from multiple modalities to a new subspace optimized for one-class classification.

General Classification

Feature Engineering for Mid-Price Prediction with Deep Learning

no code implementations10 Apr 2019 Adamantios Ntakaris, Giorgio Mirone, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis

Mid-price movement prediction based on limit order book (LOB) data is a challenging task due to the complexity and dynamics of the LOB.

Feature Engineering online learning

3D Quantum Cuts for Automatic Segmentation of Porous Media in Tomography Images

no code implementations9 Apr 2019 Junaid Malik, Serkan Kiranyaz, Riyadh Al-Raoush, Olivier Monga, Patricia Garnier, Sebti Foufou, Abdelaziz Bouras, Alexandros Iosifidis, Moncef Gabbouj, Philippe C. Baveye

Binary segmentation of volumetric images of porous media is a crucial step towards gaining a deeper understanding of the factors governing biogeochemical processes at minute scales.

Semantic Segmentation

Colorectal cancer diagnosis from histology images: A comparative study

no code implementations27 Mar 2019 Junaid Malik, Serkan Kiranyaz, Suchitra Kunhoth, Turker Ince, Somaya Al-Maadeed, Ridha Hamila, Moncef Gabbouj

Moreover, we conduct quantitative comparative evaluations among the traditional methods, transfer learning-based methods and the proposed adaptive approach for the particular task of cancer detection and identification from scarce and low-resolution histology images.

Transfer Learning

Data-driven Neural Architecture Learning For Financial Time-series Forecasting

no code implementations5 Mar 2019 Dat Thanh Tran, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis

Forecasting based on financial time-series is a challenging task since most real-world data exhibits nonstationary property and nonlinear dependencies.

Time Series Forecasting Time Series Prediction

Operational Neural Networks

no code implementations15 Feb 2019 Serkan Kiranyaz, Turker Ince, Alexandros Iosifidis, Moncef Gabbouj

In order to address this drawback and also to accomplish a more generalized model over the convolutional neurons, this study proposes a novel network model, called Operational Neural Networks (ONNs), which can be heterogeneous and encapsulate neurons with any set of operators to boost diversity and to learn highly complex and multi-modal functions or spaces with minimal network complexity and training data.

Temporal Logistic Neural Bag-of-Features for Financial Time series Forecasting leveraging Limit Order Book Data

no code implementations24 Jan 2019 Nikolaos Passalis, Anastasios Tefas, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis

However, combining existing BoF formulations with deep feature extractors pose significant challenges: the distribution of the input features is not stationary, tuning the hyper-parameters of the model can be especially difficult and the normalizations involved in the BoF model can cause significant instabilities during the training process.

Density Estimation Time Series Analysis +1

Using Deep Learning for price prediction by exploiting stationary limit order book features

no code implementations23 Oct 2018 Avraam Tsantekidis, Nikolaos Passalis, Anastasios Tefas, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis

The recent surge in Deep Learning (DL) research of the past decade has successfully provided solutions to many difficult problems.

Time Series

Compressively Sensed Image Recognition

no code implementations15 Oct 2018 Aysen Degerli, Sinem Aslan, Mehmet Yamac, Bulent Sankur, Moncef Gabbouj

Recent literature works show that compressive image classification is possible in CS domain without reconstruction of the signal.

Compressive Sensing General Classification +1

Progressive Operational Perceptron with Memory

1 code implementation20 Aug 2018 Dat Thanh Tran, Serkan Kiranyaz, Moncef Gabbouj, Alexandros Iosifidis

Generalized Operational Perceptron (GOP) was proposed to generalize the linear neuron model in the traditional Multilayer Perceptron (MLP) and this model can mimic the synaptic connections of the biological neurons that have nonlinear neurochemical behaviours.

Heterogeneous Multilayer Generalized Operational Perceptron

1 code implementation13 Apr 2018 Dat Thanh Tran, Serkan Kiranyaz, Moncef Gabbouj, Alexandros Iosifidis

Previously, Generalized Operational Perceptron (GOP) was proposed to extend conventional perceptron model by defining a diverse set of neuronal activities to imitate a generalized model of biological neurons.

Weighted Linear Discriminant Analysis based on Class Saliency Information

no code implementations19 Feb 2018 Lei Xu, Alexandros Iosifidis, Moncef Gabbouj

In this paper, we propose a new variant of Linear Discriminant Analysis to overcome underlying drawbacks of traditional LDA and other LDA variants targeting problems involving imbalanced classes.

General Classification Image Classification +1

Subspace Support Vector Data Description

1 code implementation12 Feb 2018 Fahad Sohrab, Jenni Raitoharju, Moncef Gabbouj, Alexandros Iosifidis

The method iteratively optimizes the data mapping along with data description in order to define a compact class representation in a low-dimensional feature space.

Classification General Classification

Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis

no code implementations4 Dec 2017 Dat Thanh Tran, Alexandros Iosifidis, Juho Kanniainen, Moncef Gabbouj

Financial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market.

Time Series Forecasting

Multilinear Class-Specific Discriminant Analysis

no code implementations29 Oct 2017 Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis

There has been a great effort to transfer linear discriminant techniques that operate on vector data to high-order data, generally referred to as Multilinear Discriminant Analysis (MDA) techniques.

Stock Price Prediction

Improving Efficiency in Convolutional Neural Network with Multilinear Filters

no code implementations28 Sep 2017 Dat Thanh Tran, Alexandros Iosifidis, Moncef Gabbouj

The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices.

Tensor Representation in High-Frequency Financial Data for Price Change Prediction

no code implementations5 Sep 2017 Dat Thanh Tran, Martin Magris, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis

Nowadays, with the availability of massive amount of trade data collected, the dynamics of the financial markets pose both a challenge and an opportunity for high frequency traders.

Time Series

Neural Class-Specific Regression for face verification

no code implementations31 Aug 2017 Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj

Face verification is a problem approached in the literature mainly using nonlinear class-specific subspace learning techniques.

Face Verification

Human experts vs. machines in taxa recognition

no code implementations23 Aug 2017 Johanna Ärje, Jenni Raitoharju, Alexandros Iosifidis, Ville Tirronen, Kristian Meissner, Moncef Gabbouj, Serkan Kiranyaz, Salme Kärkkäinen

Contrary to previous findings in the literature, we find that for machines following a typical flat classification approach commonly used in machine learning performs better than forcing machines to adopt a hierarchical, local per parent node approach used by human taxonomic experts ($\overline{CE}=13. 8\%$).

BIG-bench Machine Learning General Classification +1

INTEL-TUT Dataset for Camera Invariant Color Constancy Research

no code implementations21 Mar 2017 Caglar Aytekin, Jarno Nikkanen, Moncef Gabbouj

In this paper, we provide a novel dataset designed for camera invariant color constancy research.

Color Constancy

Video Ladder Networks

no code implementations6 Dec 2016 Francesco Cricri, Xingyang Ni, Mikko Honkala, Emre Aksu, Moncef Gabbouj

Thanks to the recurrent connections, the decoder can exploit temporal summaries generated from all layers of the encoder.

Probabilistic Saliency Estimation

no code implementations13 Sep 2016 Caglar Aytekin, Alexandros Iosifidis, Moncef Gabbouj

In this paper, we model the salient object detection problem under a probabilistic framework encoding the boundary connectivity saliency cue and smoothness constraints in an optimization problem.

object-detection RGB Salient Object Detection +2

Limited Random Walk Algorithm for Big Graph Data Clustering

no code implementations21 Jun 2016 Honglei Zhang, Jenni Raitoharju, Serkan Kiranyaz, Moncef Gabbouj

Graph clustering is an important technique to understand the relationships between the vertices in a big graph.

Social and Information Networks Physics and Society

On the Dynamics of a Recurrent Hopfield Network

no code implementations9 Feb 2015 Rama Garimella, Berkay Kicanaoglu, Moncef Gabbouj

In this research paper novel real/complex valued recurrent Hopfield Neural Network (RHNN) is proposed.

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