Hichem Frigui

University of Louisville | UL · Department of Computer Engineering and Computer Science

We propose a new data augmentation technique for semi-supervised learning settings that emphasizes learning from the most challenging regions of the feature space. Starting with a fully supervised reference model, we first identify low confidence predictions. These samples are then used to train a Variational AutoEncoder (VAE) that can generate an...

We propose a local feature selection method for the Multiple Instance Learning (MIL) framework. Unlike conventional feature selection algorithms that assign a global set of features to the whole data set, our algorithm, called Multiple Instance Local Salient Feature Selection (MI-LSFS), searches the feature space to find the relevant features withi...

Lung cancer is by far the leading cause of cancer death in the US. Recent studies have demonstrated the effectiveness of screening using low dose CT (LDCT) in reducing lung cancer related mortality. While lung nodules are detected with a high rate of sensitivity, this exam has a low specificity rate and it is still difficult to separate benign and...

We propose discrimination algorithms for buried threat detection (BTD) that exploit deep convolutional neural networks (CNNs) and recurrent neural networks (RNN) to analyze 2-D GPR B-scans in the down-track (DT) and cross-track (CT) directions as well as 3-D GPR volumes. Instead of imposing a specific model or handcrafted features, as in most exist...

Purpose Multiview two‐dimensional (2D) convolutional neural networks (CNNs) and three‐dimensional (3D) CNNs have been successfully used for analyzing volumetric data in many state‐of‐the‐art medical imaging applications. We propose an alternative modular framework that analyzes volumetric data with an approach that is analogous to radiologists’ int...

We propose an effcient machine learning based approach in modeling the magnetism of diluted magnetic semiconductors (DMSs) leading to the prediction of new compounds with enhanced magnetic properties. The approach combines accurate ab initio methods with statistical tools to uncover the correlation between the magnetic features of DMSs and electron...

The paper proposes a molecule specific normalization algorithm, called MSN, which adopts a robust surface fitting strategy to minimize the molecular profile difference of a group of house-keeping molecules across samples. The house-keeping molecules are those molecules whose abundance levels were not affected by the biological treatment. The applic...

Biomarker discovery, i.e., identifying the discriminative features that are responsible for alteration of a biological system, is often solved by feature selection implemented by machine learning approaches. While many individual feature selection methods are used in biomarker discovery, the nature of omics data (small number of samples, large numb...

Multiple instance regression (MIR) operates on a collection of bags, where each bag contains many instances sharing the same real-valued label. Only few instances, called primary instances, contribute to the bag labels. The remaining ones are noisy observations. The goal in MIR is to identify the primary instances within each bag and learn a regres...

In this paper, we consider the development of algorithms for the automatic detection of buried threats using ground penetrating radar (GPR) measurements. GPR is one of the most studied and successful modalities for automatic buried threat detection (BTD), and a large variety of BTD algorithms have been proposed for it. Despite this, large-scale com...

Feature selection in Liquid Chromatography-Mass Spectrometry (LC-MS)-based metabolomics data (biomarker discovery) have become an important topic for machine learning researchers. High dimensionality and small sample size of LC-MS data make feature selection a challenging task. The goal of biomarker discovery is to select the few most discriminativ...

SCoTS captures a sparse representation of shapes in an input image through a linear span of previously delineated shapes in a training repository. The model updates shape prior over level set iterations and captures variabilities in shapes by a sparse combination of the training data. The level set evolution is therefore driven by a data term as we...

Vehicle Make and Model Recognition (VMMR) plays an important role in Intelligent Transportation Systems. Due to the increase in volume and diversity of vehicles on the road, traffic monitoring has become both important and difficult. Several cues could be used in VMMR. Examples include salient features extracted from vehicle representing the shape...

Fuzzy logic is a powerful tool to model knowledge uncertainty, measurements imprecision, and vagueness. However, there is another type of vagueness that arises when data have multiple forms of expression that fuzzy logic does not address quite well. This is the case for multiple instance learning problems (MIL). In MIL, an object is represented by...

We propose a new relational clustering approach, called Fuzzy clustering with Learnable Clusterdependent Kernels (FLeCK), that learns the underlying cluster-dependent dissimilarity measure while seeking compact clusters. The learned dissimilarity is based on a Gaussian kernel function with cluster-dependent parameters. Each cluster’s parameter lear...

In this paper, a novel method of embedding shape information into level set image segmentation is proposed. Our method is based on inferring shape variations by a sparse linear combination of instances in the shape repository. Given a sufficient number of training shapes with variations, a new shape can be approximated by a linear span of training...

Recently, increasing security threats has led to video surveillance solutions being deployed and used at a greater pace. Vehicle Make and Model Recognition (VMMR) is an appealing problem because it is a well-defined fine-grained recognition task that plays an important role in many potential applications such as road traffic monitoring and manageme...

Detection of buried landmines and other explosive objects using ground penetrating radar (GPR) has been investigated for almost two decades and several classifiers have been developed. Most of these methods are based on the supervised learning paradigm where labeled target and clutter signatures are needed to train a classifier to discriminate betw...

We present a new method, based on the Fisher Vector (FV), for detecting buried explosive objects using ground- penetrating radar (GPR) data. First, low-level dense SIFT features are extracted from a grid covering a region of interest (ROIs). ROIs are identified as regions with high-energy along the (down-track, depth) dimensions of the 3-D GPR cube...

A novel fuzzy learning framework that employs fuzzy inference to solve the problem of Multiple Instance Learning (MIL) is presented. The framework introduces a new class of fuzzy inference systems called Multiple Instance Mamdani Fuzzy Inference Systems (MIMamdani). In multiple instance problems, the training data is ambiguously labeled. Instances...

We introduce an ensemble learning method for temporal data that uses a mixture of hidden Markov models (HMM). We hypothesize that the data are generated by K models, each of which reflects a particular trend in the data. The proposed approach, called ensemble HMM (eHMM), is based on clustering within the log-likelihood space and has two main steps....

We present a robust speaker identification algorithm that uses novel features based on soft bag-of-word representation and a simple Naive Bayes classifier. The bag-of-words (BoW) based histogram feature descriptor is typically constructed by summarizing and identifying representative prototypes from low-level spectral features extracted from traini...

A new class of subpixel target detection algorithms that use a local structured background model is introduced. Our approach, referred to as Context Dependent Target Detectors, extends existing structured detectors to multiple contexts. It is based on a robust context dependent spectral unmixing algorithm that uses multiple linear models to take in...

A robust hyperspectral unmixing algorithm that finds multiple sets of endmembers is introduced. The algorithm, called Robust Context Dependent Spectral Unmixing (RCDSU), combines the advantages of context dependent unmixing and robust clustering. RCDSU adapts the unmixing to different regions, or contexts, of the spectral space. It combines fuzzy a...

We present a fusion method, based on fuzzy inference, for detecting buried objects using ground-penetrating radar (GPR) data. The performance of different discrimination algorithms can vary significantly depending on the target type, burial orientation, and other environmental conditions. In some cases, algorithms can provide complementary evidence...

Spectral unmixing is a challenging, ill-posed, inverse problem. Many algorithms have been proposed for robust, stable, and accurate unmixing solutions. Different algorithms have different modes of operation and usually yield different results. Moreover, most of them require specifying the number of endmembers to be extracted before hand. We propose...

We present a fusion method, based on fuzzy inference, for detecting buried objects using ground-penetrating radar (GPR) data. The GPR sensor generates 3-dimensional data that correspond to depth, down-track, and cross-track. Most discrimination algorithms process only 2-D slices of the 3-D cube: (down-track, depth) or (cross-track, depth). The perf...

We propose a possibilistic approach for Generalized Dirichlet mixture parameter estimation, data clustering, and feature weighting. The proposed algorithm, called Robust and Unsupervised Learning of Finite Generalized Dirichlet Mixture Models (RULe_GDM), exploits a property of the Generalized Dirichlet distributions that transforms the data to make...

Medical simulations, where uncommon clinical situations can be replicated, have proved to provide a more comprehensive training. Simulations involve the use of patient simulators, which are lifelike mannequins. After each session, the physician must manually review and annotate the recordings and then debrief the trainees. The physician responsible...

For real-world clustering tasks, the input data is typically not easily separable due to the highly complex data structure or when clusters vary in size, density and shape. Kernel-based clustering has proven to be an effective approach to partition such data. In this paper, we provide an overview of several fuzzy kernel clustering algorithms. We fo...

We propose a multi-stream continuous hidden Markov model (MSCHMM) framework that can learn from multiple modalities. We assume that the feature space is partitioned into subspaces generated by different sources of information. In order to fuse the different modalities, the proposed MSCHMM introduces stream relevance weights. First, we modify the pr...

Spectral unmixing is a challenging, ill-posed, inverse problem that may result in infinitely many solutions, most of which are meaningless. Constraints must be added to guide the search process and narrow the space of possible solutions. Multiple sources of information can be used to find such constraints. In this paper, we introduce a semi-supervi...

We propose a new semi-supervised relational clustering approach, called Semi-Supervised relational clustering with local scaling parameter (SS-LSL). The proposed algorithm learns a cluster dependent Gaussian kernel while finding compact clusters. SS-LSL uses side-information in the form of a small set of constraints on which instances should or sho...

Many machine learning applications rely on learning distance functions with side information. Most of these distance metric learning approaches learns a Mahalanobis distance. While these approaches may work well when data is in low dimensionality, they become computationally expensive or even unfeasible for high dimensional data. In this paper, we...

We introduce a new fuzzy semi-supervised clustering technique with adaptive local distance measure (SURF-LDML). The proposed algorithm learns the underlying cluster-dependent dissimilarity measure while finding compact clusters in the given data set. This objective is achieved by integrating penalty and reward cost functions in the objective functi...

Multiple Instance Learning is a recently researched learning paradigm in machine intelligence which operates under conditions of uncertainty with the cost of increased computational burden. This increase in computational burden can be avoided by embedding these so-called multiple instances using a kernel function or other embedding function. In the...

A hyperspectral endmember detection and spectral unmixing algorithm that finds multiple sets of endmembers is presented. Hyperspectral data are often nonconvex. The Piecewise Convex Multiple-Model Endmember Detection algorithm accounts for this using a piecewise convex model. Multiple sets of endmembers and abundances are found using an iterative f...

We propose a machine learning based speaker segmentation and identification system that provides the physician with automated tools to segment, semantically index and retrieve specific segments from a large database of medical simulation video sessions. Instead of working directly in the original feature space, our approach maps low-level audio fea...

We propose a feature level fusion that is based on mapping the original low-level audio features to histogram descriptors. Our mapping is based on possibilistic membership functions and has two main components. The first one consists of clustering each set of features and identifying a set of representative prototypes. The second component uses the...

A hyperspectral endmember detection and spectral unmixing algorithm that finds multiple sets of endmembers is presented. This algorithm, the Piece-wise Convex Multiple Model Endmember Detection (P-COMMEND) algorithm, models a hyperspectral image using a piece-wise convex representation. By using a piece-wise convex representation, non-convex hypers...

A hyperspectral unmixing algorithm that finds multiple sets of endmembers is introduced. The algorithm, called Context Dependent Spectral Unmixing (CDSU), is a local approach that adapts the unmixing to different regions of the spectral space. It is based on a novel objective function that combines context identification and unmixing into a joint f...

We propose a novel image database categorisation approach using Robust Modelling of finite Generalised Dirichlet Mixture (RM-GDM). The proposed algorithm is based on optimising an objective function that associates two types of memberships with each data sample. The first one is the posterior probability and indicates how well a sample fits each es...

While classical kernel-based clustering algorithms are based on a single kernel, in practice it is often desirable to base clustering on combination of multiple kernels. In [1], we considered a fuzzy c-means with multiple kernels in observation space (FCMK-OS) algorithm which constructs the kernel from a number of Gaussian kernels and learns a reso...

Hidden Markov Models (HMM) have proved to be eective for detecting buried land mines using data collected by a moving-vehicle-mounted ground penetrating radar (GPR). The general framework for a HMM-based landmine detector consists of building a HMM model for mine signatures and a HMM model for clutter signatures. A test alarm is assigned a condence...

Many algorithms have been proposed for detecting anti-tank landmines and discriminating between mines and clutter objects using data generated by a ground penetrating radar (GPR) sensor. Our extensive testing of some of these algorithms has indicated that their performances are strongly dependent upon a variety of factors that are correlated with g...

In this paper, the relational fuzzy c-means clustering algorithm is extended to an adaptive cluster model which maps data points to a high dimensional feature space through an optimal convex combination of homogenous kernels with respect to each cluster. This generalized model, called Relational Fuzzy C-Means with Multiple Kernels (RFCM-MK), strive...

We propose a novel image database categorization approach using robust unsupervised learning of finite generalized dirichlet mixture models with feature discrimination. The proposed algorithm is based on optimizing an objective function that associates two types of memberships with each data sample. The first one is the posterior probability and in...

We propose a landmine detection algorithm using ground penetrating radar (GPR) data that uses multiple features and an ensemble of continuous hidden Markov models (CHMMs). Our approach is motivated by the need for different features and multiple models to capture the large variations of mine and clutter types and the different environmental conditi...

The Edge Histogram Detector (EHD) is a well-researched and tested algorithm that has been integrated into fielded systems for landmine detection using Ground Penetrating Radar (GPR) sensor. It uses edge histogram based features and a possibilistic K-Nearest Neighbors (KNN) classifier. Due to the inherent static data representation and static classi...

We propose a multistream discrete hidden Markov model (DHMM) framework and apply it to the problem of land-mine detection using ground-penetrating radar (GPR). We hypothesize that each signature (mine or nonmine) can be characterized better by multiple synchronous sequences representing features that capture different environments and different rad...

We propose a new relational clustering approach, called Fuzzy clustering with Learnable Cluster dependent Kernels (FLeCK), that learns multiple kernels while seeking compact clusters. A Gaussian kernel is learned with respect to each cluster. It reflects the relative density, size, and position of the cluster with respect to the other clusters. The...

Multiple instance learning (MIL) is a technique used for learning a target concept in the presence of noise or in a condition of uncertainty. While standard learning techniques present the learner with individual samples, MIL alternatively presents the learner with sets of samples. Although sets are the primary elements used for analysis in MIL, re...

In this paper, the kernel fuzzy c-means clustering algorithm is extended to an adaptive cluster model which maps data points to a high dimensional feature space through an optimal convex combination of homogenous kernels with respect to each cluster. This generalized model, called Fuzzy C- Means with Multiple Kernels (FCM-MK), strives to find a goo...

We propose a novel method for fusing different classifiers outputs. Our approach, called Context Extraction for Local Fusion with Neural Networks (CELF-NN), is a local approach that adapts Artificial Neural Network fusion method to different regions of the feature space. It is based on a novel objective function that combines context identification...

We propose a novel method for fusing different classifiers outputs. Our approach, called Context Extraction for Local Fusion with Fuzzy Integrals (CELF-FI), is a local approach that adapts fuzzy integrals fusion method to different regions of the feature space. It is based on a novel objective function that combines context identification and multi...

We propose a novel possibilistic clustering algorithm based on robust modelling of the Generalized Dirichlet (GD) finite mixture. The algorithm generates two types of membership degrees. The first one is a posterior probability that indicates the degree to which the point fits the estimated distribution. The second membership represents the degree...

We introduce a new fuzzy relational clustering technique with Local Scaling Parameter Learning (LSPL). The proposed approach learns the underlying cluster dependent dissimilarity measure while finding compact clusters in the given data set. The learned measure is a Gaussian similarity function defined with respect to each cluster that allows to con...

The piece-wise convex multiple model endmember detection algorithm (P-COMMEND) and the Piece-wise Convex End-member detection (PCE) algorithm autonomously estimate many sets of endmembers to represent a hyperspectral image. A piece-wise convex model with several sets of endmembers is more effective for representing non-convex hyperspectral imagery...

An endmember detection and spectral unmixing algorithm that uses both spatial and spectral information is presented. This method, Spatial Piece-wise Convex Multiple Model Endmember Detection (Spatial P-COMMEND), autonomously estimates multiple sets of endmembers and performs spectral unmixing for input hyperspectral data. Spatial P-COMMEND does not...

We propose a novel image database categorization approach using a possibilistic clustering algorithm. The proposed algorithm is based on a robust data modeling using the Generalized Dirichlet (GD) finite mixture and generates two types of membership degrees. The first one is a posterior probability that indicates the degree to which the point fits...

We propose a landmine detection algorithm using ground penetrating radar data that is based on an SVM classifier. The kernel function for the SVM is constructed using discrete hidden Markov modeling (HMM). Typically, the kernel matrix could be obtained by defining an adequate similarity measure in the feature space. However, this approach is inappr...

We propose a discriminative method for combining heterogeneous sets of features for the continuous hidden Markov model classifier. We use a model level fusion approach and apply it to the problem of landmine detection using ground penetrating radar (GPR). We hypothesize that each signature (mine or non-mine) can be characterized better by multiple...

Context extraction for local fusion (CELF) is a local approach that combines multiple classifier outputs with the help of feature space information. CELF is based on an objective function that integrates context extraction and decision fusion. Context extraction divides the feature space into homogeneous regions; decision fusion combines multiple c...

We present a novel method for fusing the results of multiple land mine detection algorithms which use different sensors, features, and different classification methods. The proposed multisensor/multialgorithm fusion method, which is called context-dependent fusion (CDF), is motivated by the fact that the relative performance of different sensors an...

We introduce a new spectral mixture analysis approach. Unlike most available approaches that only use the spectral information, this approach uses the spectral and spatial information available in the hyperspectral data. Moreover, it does not assume a global convex geometry model that encompasses all the data but rather multiple local convex models...

We propose a landmine detection algorithm that uses ensemble discrete hidden Markov models with context dependent training schemes. We hypothesize that the data are generated by K models. These different models reflect the fact that mines and clutter objects have different characteristics depending on the mine type, soil and weather conditions, and...

The Edge Histogram Detector (EHD) is a landmine detection algorithm that has been developed for ground penetrating radar (GPR) sensor data. It has been tested extensively and has demonstrated excellent performance. The EHD consists of two main components. The first one maps the raw data to a lower dimension using edge histogram based feature descri...

Multiple instance learning (MIL) is a technique used for identifying a target pattern within sets of data. In MIL, a learner is presented with sets of samples; whereas in standard techniques, a learner is presented with individual samples. The MI scenario is encountered given the nature of landmine detection in GPR data, and therefore landmine dete...

We present a novel method for fusing the decisions of multiple classification algorithms which use different features, classification methods, and data sources. The proposed method, called context dependent fusion of multiple algorithms (CDF-MA) is motivated by the fact that the relative performance of different algorithms can vary significantly as...

In this paper, we propose a new general low-level feature representation for audio signals. Our approach, called Dominant Audio Descriptor is inspired by the MPEG-7 Dominant Color Descriptor. It is based on clustering time-local features and identifying dominant components. The features used to illustrate this approach are the well-known Mel Freque...

We propose a modified discrete HMM that handles multimodalities. We assume that the feature space is partitioned into subspaces generated by different sources of information. To combine these heteregoneous modalities we propose a multi-stream discrete HMM that assigns a relevance weight to each subspace. The relevance weights are set local and depe...

This paper describes the Ensemble Possibilistic K-NN algorithm for classification of gene expression profiles into three major cancer categories. In fact, a modification of forward feature selection is proposed to identify relevant feature subsets allowing for multiple possibilistic K-nearest neighbors (pK-NNs) rule experts. First, individual featu...

We present a novel method for fusing different classifiers outputs. Our approach, called Context Extraction for Local Fusion with Feature Discrimination (CELF-FD), is a local approach that adapts the fusion method to different regions of the feature space. It is based on a novel objective function that combines context identification and multi-algo...

We propose an image annotation approach that relies on fuzzy clustering and feature discrimination, a greedy selection and joining algorithm (GSJ), and Bayes rule. Clustering is used to group image regions into prototypical region clusters that summarize the training data and can be used as the basis of annotating new test images. Since this proble...

Principal component analysis (PCA) is a mathematical method that reduces the dimensionality of the data while retaining most of the variation in the data. Although PCA has been applied in many areas successfully, it suffers from sensitivity to noise and is limited to linear principal components. The noise sensitivity problem comes from the least-sq...