Task guided representation learning using compositional models for zero-shot domain adaptation.

Zero-shot domain adaptation (ZDA) methods aim to transfer knowledge about a task learned in a source domain to a target domain, while task-relevant data from target domain are not available. In this work, we address learning feature representations which are invariant to and shared among different domains considering task characteristics for ZDA. To this end, we propose a method for task-guided ZDA (TG-ZDA) which employs multi-branch deep neural networks to learn feature representations exploiting their domain invariance and shareability properties. The proposed TG-ZDA models can be trained end-to-end without requiring synthetic tasks and data generated from estimated representations of target domains. The proposed TG-ZDA has been examined using benchmark ZDA tasks on image classification datasets. Experimental results show that our proposed TG-ZDA outperforms state-of-the-art ZDA methods for different domains and tasks.

Deep Depth Completion From Extremely Sparse Data: A Survey.

Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map captured from a depth sensor, e.g., LiDARs. It plays an essential role in various applications such as autonomous driving, 3D reconstruction, augmented reality, and robot navigation. Recent successes on the task have been demonstrated and dominated by deep learning based solutions. In this article, for the first time, we provide a comprehensive literature review that helps readers better grasp the research trends and clearly understand the current advances. We investigate the related studies from the design aspects of network architectures, loss functions, benchmark datasets, and learning strategies with a proposal of a novel taxonomy that categorizes existing methods. Besides, we present a quantitative comparison of model performance on three widely used benchmarks, including indoor and outdoor datasets. Finally, we discuss the challenges of prior works and provide readers with some insights for future research directions.

Joint Adversarial Example and False Data Injection Attacks for State Estimation in Power Systems.

Although state estimation using a bad data detector (BDD) is a key procedure employed in power systems, the detector is vulnerable to false data injection attacks (FDIAs). Substantial deep learning methods have been proposed to detect such attacks. However, deep neural networks are susceptible to adversarial attacks or adversarial examples, where slight changes in inputs may lead to sharp changes in the corresponding outputs in even well-trained networks. This article introduces the joint adversarial example and FDIAs (AFDIAs) to explore various attack scenarios for state estimation in power systems. Considering that perturbations added directly to measurements are likely to be detected by BDDs, our proposed method of adding perturbations to state variables can guarantee that the attack is stealthy to BDDs. Then, malicious data that are stealthy to both BDDs and deep learning-based detectors can be generated. Theoretical and experimental results show that our proposed state-perturbation-based AFDIA method (S-AFDIA) can carry out attacks stealthy to both conventional BDDs and deep learning-based detectors, while our proposed measurement-perturbation-based adversarial FDIA method (M-AFDIA) succeeds if only deep learning-based detectors are used. The comparative experiments show that our proposed methods provide better performance than state-of-the-art methods. Besides, the ultimate effect of attacks can also be optimized using the proposed joint attack methods.

Gender classification using mesh networks on multiresolution multitask fMRI data.

Brain connectivity networks have been shown to represent gender differences under a number of cognitive tasks. Recently, it has been conjectured that fMRI signals decomposed into different resolutions embed different types of cognitive information. In this paper, we combine multiresolution analysis and connectivity networks to study gender differences under a variety of cognitive tasks, and propose a machine learning framework to discriminate individuals according to their gender. For this purpose, we estimate a set of brain networks, formed at different resolutions while the subjects perform different cognitive tasks. First, we decompose fMRI signals recorded under a sequence of cognitive stimuli into its frequency subbands using Discrete Wavelet Transform (DWT). Next, we represent the fMRI signals by mesh networks formed among the anatomic regions for each task experiment at each subband. The mesh networks are constructed by ensembling a set of local meshes, each of which represents the relationship of an anatomical region as a weighted linear combination of its neighbors. Then, we estimate the edge weights of each mesh by ridge regression. The proposed approach yields 2CL functional mesh networks for each subject, where C is the number of cognitive tasks and L is the number of subband signals obtained after wavelet decomposition. This approach enables one to classify gender under different cognitive tasks and different frequency subbands. The final step of the suggested framework is to fuse the complementary information of the mesh networks for each subject to discriminate the gender. We fuse the information embedded in mesh networks formed for different tasks and resolutions under a three-level fuzzy stacked generalization (FSG) architecture. In this architecture, different layers are responsible for fusion of diverse information obtained from different cognitive tasks and resolutions. In the experimental analyses, we use Human Connectome Project task fMRI dataset. Results reflect that fusing the mesh network representations computed at multiple resolutions for multiple tasks provides the best gender classification accuracy compared to the single subband task mesh networks or fusion of representations obtained using only multitask or only multiresolution data. Besides, mesh edge weights slightly outperform pairwise correlations between regions, and significantly outperform raw fMRI signals. In addition, we analyze the gender discriminative power of mesh edge weights for different tasks and resolutions.

Encoding the local connectivity patterns of fMRI for cognitive task and state classification.

In this work, we propose a novel framework to encode the local connectivity patterns of brain, using Fisher vectors (FV), vector of locally aggregated descriptors (VLAD) and bag-of-words (BoW) methods. We first obtain local descriptors, called mesh arc descriptors (MADs) from fMRI data, by forming local meshes around anatomical regions, and estimating their relationship within a neighborhood. Then, we extract a dictionary of relationships, called brain connectivity dictionary by fitting a generative Gaussian mixture model (GMM) to a set of MADs, and selecting codewords at the mean of each component of the mixture. Codewords represent connectivity patterns among anatomical regions. We also encode MADs by VLAD and BoW methods using k-Means clustering. We classify cognitive tasks using the Human Connectome Project (HCP) task fMRI dataset and cognitive states using the Emotional Memory Retrieval (EMR). We train support vector machines (SVMs) using the encoded MADs. Results demonstrate that, FV encoding of MADs can be successfully employed for classification of cognitive tasks, and outperform VLAD and BoW representations. Moreover, we identify the significant Gaussians in mixture models by computing energy of their corresponding FV parts, and analyze their effect on classification accuracy. Finally, we suggest a new method to visualize the codewords of the learned brain connectivity dictionary.

Hierarchical multi-resolution mesh networks for brain decoding.

Human brain is supposed to process information in multiple frequency bands. Therefore, we can extract diverse information from functional Magnetic Resonance Imaging (fMRI) data by processing it at multiple resolutions. We propose a framework, called Hierarchical Multi-resolution Mesh Networks (HMMNs), which establishes a set of brain networks at multiple resolutions of fMRI signal to represent the underlying cognitive process. Our framework, first, decomposes the fMRI signal into various frequency subbands using wavelet transform. Then, a brain network is formed at each subband by ensembling a set of local meshes. Arc weights of each local mesh are estimated by ridge regression. Finally, adjacency matrices of mesh networks obtained at different subbands are used to train classifiers in an ensemble learning architecture, called fuzzy stacked generalization (FSG). Our decoding performances on Human Connectome Project task-fMRI dataset reflect that HMMNs can successfully discriminate tasks with 99% accuracy, across 808 subjects. Diversity of information embedded in mesh networks of multiple subbands enables the ensemble of classifiers to collaborate with each other for brain decoding. The suggested HMMNs decode the cognitive tasks better than a single classifier applied to any subband. Also mesh networks have a better representation power compared to pairwise correlations or average voxel time series. Moreover, fusion of diverse information using FSG outperforms fusion with majority voting. We conclude that, fMRI data, recorded during a cognitive task, provide diverse information in multi-resolution mesh networks. Our framework fuses this complementary information and boosts the brain decoding performances obtained at individual subbands.

Machine Learning Methods for Attack Detection in the Smart Grid.

Attack detection problems in the smart grid are posed as statistical learning problems for different attack scenarios in which the measurements are observed in batch or online settings. In this approach, machine learning algorithms are used to classify measurements as being either secure or attacked. An attack detection framework is provided to exploit any available prior knowledge about the system and surmount constraints arising from the sparse structure of the problem in the proposed approach. Well-known batch and online learning algorithms (supervised and semisupervised) are employed with decision- and feature-level fusion to model the attack detection problem. The relationships between statistical and geometric properties of attack vectors employed in the attack scenarios and learning algorithms are analyzed to detect unobservable attacks using statistical learning methods. The proposed algorithms are examined on various IEEE test systems. Experimental analyses show that machine learning algorithms can detect attacks with performances higher than attack detection algorithms that employ state vector estimation methods in the proposed attack detection framework.

Functional Mesh Model with Temporal Measurements for brain decoding.

We propose a method called Functional Mesh Model with Temporal Measurements (FMM-TM) to estimate a functional relationship among voxels using temporal data, and employ these relationships for brain decoding. For each sample, we measure Blood Oxygenation Level Dependent (BOLD) responses from each voxel, and construct a functional mesh around each voxel (called seed voxel) with its nearest neighbors selected using distance metrics namely Pearson correlation, cosine similarity and Euclidean distance. Then, we represent the BOLD response of a seed voxel in terms of linear combination of BOLD responses of its p-nearest neighbors. The relationship between the seed voxel and its neighbors is represented using a set of weights which are estimated by employing linear regression. We train Support Vector Machine and k-Nearest Neighbor classifiers using the estimated weights as features. We test our model in an event-related design experiment, namely object recognition, and observe that our features perform better than raw voxel intensity values, features obtained using various pairwise distance metrics, and local mesh model features extracted using stationary and temporal measurements.

Analyzing the information distribution in the fMRI measurements by estimating the degree of locality.

In this study, we propose a new method for analyzing and representing the distribution of discriminative information for data acquired via functional Magnetic Resonance Imaging (fMRI). For this purpose, we form a spatially local mesh with varying size, around each voxel, called the seed voxel. The relationship among each seed voxel and its neighbors is estimated using a linear regression model by minimizing the square error. Then, we estimate the optimal mesh size that represents the connections among each seed voxel and its surroundings by minimizing Akaike's Final Prediction Error (FPE) with respect to the mesh size. The degree of locality is represented by the optimum mesh size. Our results indicate that the local mesh size with the highest discriminative power varies across individual participants. The proposed method was tested on an fMRI study consisting of item recognition (IR) and judgment of recency (JOR) tasks. For each participant, the estimated arc weights of each local mesh with different mesh size are used to classify the type of memory judgment (i.e.IR or JOR). Classification accuracy for each participant was derived using k-Nearest Neighbor (k-NN) method. The results indicate that the proposed local mesh model with optimal mesh size can successfully represent discriminative information for neuroimaging data.

Representation of cognitive processes using the minimum spanning tree of local meshes.

A new graphical model called Cognitive Process Graph (CPG) is proposed, for classifying cognitive processes based on neural activation patterns which are acquired via functional Magnetic Resonance Imaging (fMRI) in brain. In the CPG, first local meshes are formed around each voxel. Second, the relationships between a voxel and its neighbors in a local mesh, which are estimated by using a linear regression model, are used to form the edges among the voxels (graph nodes) in the CPG. Then, a minimum spanning tree (MST) of the CPG which spans all the voxels in the region of interest is computed. The arc weights of the MST are used to represent the underlying cognitive processes. The proposed method reduces the curse of dimensionality problem that is caused by very large dimension of the feature space of the fMRI measurements, compared to number of instances. Finally, the arc weights computed over the path of the MST called MST-Features (MST-F) are used to train a statistical learning machine. The proposed method is tested on a recognition memory experiment, including data pertaining to encoding and retrieval of words belonging to ten different semantic categories. Two popular classifiers, namely k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM), are trained in order to predict the semantic category of the item being retrieved, based on activation patterns during encoding. The classification performance of the proposed learning modelis superior to the classical multi-voxel pattern analysis (MVPA) methods for the underlying cognitive process.

A new hole density as a stability measure for boron fullerenes.

We investigate the stability of boron fullerene sets B76, B78 and B82. We evaluate the ground state energies, nucleus-independent chemical shift (NICS), the binding energies per atom and the band gap values by means of first-principles methods. We construct our fullerene design by capping of pentagons and hexagons of B60 cages in such a way that the total number of atoms is preserved. In doing so, a new hole density definition is proposed such that each member of a fullerene group has a different hole density which depends on the capping process. Our analysis reveals that each boron fullerene set has its lowest-energy configuration around the same normalized hole density and the most stable cages are found in the fullerene groups which have a relatively large difference between the maximum and the minimum hole densities. The result is a new stability measure relating the cage geometry characterized by the hole density to the relative energy.