Search

Recognizing actions from still images has been popularly studied recently. In this paper, we model an action class as a flexible number of spatial configurations of body parts by proposing a new spatial sum–product network (SPN). First, we discover a set of parts in image collections via unsupervised learning. Then, our new spatial SPN is applied to model the spatial relationship and also the high-order correlations of parts. To learn robust networks, we further develop a hierarchical spatial SPN method, which models pairwise spatial relationship between parts inside subimages and models the correlation of subimages via extra layers of SPN. Our method is shown to be effective on two benchmark data sets. [ABSTRACT FROM PUBLISHER]

The corrosion of transformers by multiple sulfides seriously affects the safe operation of transformers. However, there is a lack of quantitative characterization of the extent to which temperature and oxygen as well as changes in sulfide species affect the aging of oil–paper insulation. In this study, the aging characteristics of oil–paper insulation systems were analyzed in terms of the moisture in the oil, moisture in the paper, acid value, and furfural in the presence of multiple sulfides, where the temperature and the oxygen concentration are used as independent variables. A strong positive correlation between the acid value and the furfural obtained by means of Spearman’s correlation analysis. The acid value and furfural content in the oil were then analyzed and compared according to a nonparametric test, and it was found that both the oxygen changes and the temperature changes had a relatively obvious effect on the acid value in the oil. The effect of the temperature change on the furfural was greater than the effect of the oxygen change on the furfural. Finally, a multiple linear regression analysis was performed for the change in the acid value of the oil with the change in the oxygen content and temperature to obtain the linear fitting formulas for the effects of the time, temperature, oxygen content percentage, and sulfide groups on the acid value. This study can be used to quantify the magnitude of the influences of the oxygen, temperature sulfide groups, and other factors on the aging characteristic parameters of the oil–paper insulation system and to provide a certain reference for studying the quantitative characterization of the sulfur corrosion degree by using the change in the acid value in oil. [ABSTRACT FROM AUTHOR]

In this paper, the sequence families of which maximum correlation is determined by the Weil bound of exponential sums are revisited. Using the same approach, two new constructions with large family sizes and low maximum correlation are given. The first construction is an analog of one recent result derived from the interleaved structure of Sidel'nikov sequences. For a prime p and an integer M\vert (p-1), the new M-ary sequence families of period p are obtained from irreducible quadratic polynomials and known power residue-based sequence families. The new sequence families increase family sizes of the known power residue-based sequence families, but keep the maximum correlation unchanged. In the second construction, the sequences derived from the Weil representation are generalized, where each new sequence is the elementwise product of a modulated Sidel'nikov sequence and a modulated trace sequence. For positive integers d

Event logs that are recorded by information systems provide a valuable starting point for the analysis of processes in various domains, reaching from healthcare, through logistics, to e-commerce. Specifically, behavioral patterns discovered from an event log enable operational insights, even in scenarios where process execution is rather unstructured and shows a large degree of variability. While such behavioral patterns capture frequently recurring episodes of a process’ behavior, they are not limited to sequential behavior but include notions of concurrency and exclusive choices. Existing algorithms to discover behavioral patterns are context-agnostic, though. They neglect the context in which patterns are observed, which severely limits the granularity at which behavioral regularities are identified. In this paper, we therefore present an approach to discover contextual behavioral patterns. Contextual patterns may be frequent solely in a certain partition of the event log, which enables fine-granular insights into the aspects that influence the conduct of a process. Moreover, we show how to analyze the discovered contextual behavioral patterns in terms of causal relations between context information and the patterns, as well as correlations between the patterns themselves. A complete analysis methodology leveraging all the tools presented in the paper and supplemented by interpretations guidelines is also provided. Finally, experiments with real-world event logs demonstrate the effectiveness of our techniques in obtaining fine-granular process insights. [ABSTRACT FROM AUTHOR]

Human beings tend to learn unknown knowledge in a gradual process, from the basic to the complex. Based on this point, we propose a progressive learning method for producing service strategies according to requests, with a hierarchical priori knowledge and reinforcement learning. Service strategy aims to guide how to perform home services and takes into consideration the relationship between actions and objects in home environment. In this paper, strategy generation is regarded as a text generation problem in question answering (QA). Firstly, a hierarchical priori knowledge with service-object correlation at the bottom and action-object correlation at the top is constructed to assist the understanding on the relationship of objects and actions in service strategies. Service-object correlation guides how to select proper objects with the correct order, while action-object correlation associates actions in strategies according to selected objects. Based on the hierarchical priori knowledge, a progressive learning method is proposed to make the model produce effective strategies with a sequential cognition, from service-object correlation (objects) to action-object correlation (actions). After that, reinforcement learning is employed to enhance the progressive guidance, by designing rewards in terms of the hierarchical priori knowledge. Finally, the proposed method is tested with both comparative experiments and ablation studies, and the experimental results demonstrate the superiority in producing comprehensive and logical strategies, indicating that the progressive learning method in our paper can further improve the QA performance. [ABSTRACT FROM AUTHOR]

Objective: Resting-state functional magnetic resonance imaging (rs-fMRI)-derived functional connectivity (FC) patterns have been extensively used to delineate global functional organization of the human brain in healthy development and neuropsychiatric disorders. In this paper, we investigate how FC in males and females differs in an age prediction framework. Methods: We first estimate FC between regions-of-interest (ROIs) using distance correlation instead of Pearson’s correlation. Distance correlation, as a multivariate statistical method, explores spatial relations of voxel-wise time courses within individual ROIs and measures both linear and nonlinear dependence, capturing more complex between-ROI interactions. Then, we propose a novel non-convex multi-task learning (NC-MTL) model to study age-related gender differences in FC, where age prediction for each gender group is viewed as one task, and a composite regularizer with a combination of the non-convex $\ell _{2,1-2}$ and $\ell _{1-2}$ terms is introduced for selecting both common and task-specific features. Results and Conclusion: We validate the effectiveness of our NC-MTL model with distance correlation-based FC derived from rs-fMRI for predicting ages of both genders. The experimental results on the Philadelphia Neurodevelopmental Cohort demonstrate that our NC-MTL model outperforms several other competing MTL models in age prediction. We also compare the age prediction performance of our NC-MTL model using FC estimated by Pearson’s correlation and distance correlation, which shows that distance correlation-based FC is more discriminative for age prediction than Pearson’s correlation-based FC. Significance: This paper presents a novel framework for functional connectome developmental studies, characterizing developmental gender differences in FC patterns. [ABSTRACT FROM AUTHOR]

The use of antenna arrays is indispensable in radar and multiple-input multiple-output (MIMO) wireless communications areas, as it permits the treatment of wavefronts in the spatial domain, enabling important applications such as beamforming and target detection. Spatial information is commonly given in terms of spatial correlation functions (SCFs), but its representation in terms of angular domain, such as the power azimuth spectrums (PASs), is sometimes more convenient. Therefore, transforming from SCF to PAS, and vice versa, is often required. This is commonly done by employing so-called beamformers, where the Bartlett beamformer (BB) is the most commonly utilized. However, the use of beamformers alone is not enough for retrieving PAS information from a given SCF. Particularly, this paper shows that a non-linear operation is missing in relating SCFs to PASs as provided by current beamformers. The paper also shows the mathematical expressions that correctly relate SCFs to PASs and wavenumber spectrums (WNSs) for the general case of systems with antenna arrays. The developed theory results in two new beamformers, which, corroborated by simulation results, solve any previous inconsistency in estimating PASs from SCFs. [ABSTRACT FROM AUTHOR]

The signal-to-noise ratio of optical emission spectroscopy (OES) data has decreased as the plasma etching process has advanced. As a result, not only the advanced endpoint detection method was required, but also the selection of more informative wavelengths. This paper proposes an improved endpoint detection algorithm by combining data-driven wavelength selection and a Gaussian mixture model (GMM). The data-driven wavelength selection algorithm finds the correlation between training data and a sigmoid function of time. Then, using the fitted GMM of the training data in latent space, the endpoint of the test data is determined in real-time. The proposed algorithm’s performance was evaluated using real OES data, comprised of seven operations. The correlation-based wavelength selection algorithm significantly reduced detection error by 70.2% when compared to the conventional method, which selects a few wavelengths manually based on prior knowledge. Additionally, the GMM detection method clustered OES data from low open area wafers much more clearly than the recently proposed method using GMM. This demonstrates that combining correlation-based wavelength selection with GMM is an effective method for detecting endpoints during plasma etching of small open area wafers. [ABSTRACT FROM AUTHOR]

Spatial modulation (SM) is one special type of multiple-input multiple-output (MIMO) technique whose advantage is that only one radio-frequency (RF) chain is needed. Recently, the so-called cross Z-complementary pair (CZCP) was proposed as the SM training sequence. Optimal channel estimation performance over frequency-selective channels can be achieved since the CZCPs have the specific zero correlation zone (ZCZ) for auto-correlation and cross-correlation sums. However, the ZCZ width of the CZCP is theoretically upper bounded by half sequence length. In this paper, the CZCP is extended to the cross Z-complementary set (CZCS) to have larger ZCZ width which can be used in SM to combat larger delay spread. Several generic constructions of CZCSs with large ZCZ widths and flexible lengths are proposed in this paper. Even the perfect CZCS, whose ZCZ width has the maximum value, can be obtained. Numerical simulations demonstrate that the proposed CZCS-based training sequence can tolerate large delay spreads to improve the channel estimation performance in SM. [ABSTRACT FROM AUTHOR]

Previous 2D saliency detection methods extract salient cues from a single view and directly predict the expected results. Both traditional and deep-learning-based 2D methods do not consider geometric information of 3D scenes. Therefore the relationship between scene understanding and salient objects cannot be effectively established. This limits the performance of 2D saliency detection in challenging scenes. In this paper, we show for the first time that saliency detection problem can be reformulated as two sub-problems: light field synthesis from a single view and light-field-driven saliency detection. This paper first introduces a high-quality light field synthesis network to produce reliable 4D light field information. Then a novel light-field-driven saliency detection network is proposed, in which a Direction-specific Screening Unit (DSU) is tailored to exploit the spatial correlation among multiple viewpoints. The whole pipeline can be trained in an end-to-end fashion. Experimental results demonstrate that the proposed method outperforms the state-of-the-art 2D, 3D and 4D saliency detection methods. Our code is publicly available at https://github.com/OIPLab-DUT/ESCNet. [ABSTRACT FROM AUTHOR]

Coded caching is a promising technique to smooth out network traffic by storing part of the library content at the users’ local caches. The seminal work on coded caching for single file retrieval by Maddah-Ali and Niesen (MAN) showed the existence of a global caching gain that scales with the total memory in the system, in addition to the known local caching gain in uncoded systems. This paper formulates a novel cache-aided matrix multiplication retrieval problem, relevant for data analytics and machine learning applications. In the considered problem, each cache-aided user requests the product of two matrices from the library. A structure-agnostic solution is to treat each possible matrix product as an independent file and use the MAN coded caching scheme for single file retrieval. This paper proposes two structure-aware schemes, which partition each matrix in the library by either rows or columns and let a subset of users cache some sub-matrices, that improve on the structure-agnostic scheme. For the case where the library matrices are “fat” matrices, the structure-aware row-partition scheme is shown to be order optimal under some constraint. [ABSTRACT FROM AUTHOR]

Superdirective arrays have been extensively studied because of their considerable potential accompanied, unfortunately, by a high sensitivity to random errors that affect the responses and positions of array elements. However, the statistics of their actual beam pattern (BP) has never been systematically investigated. This paper shows that the Rician probability density function (PDF), sometimes adopted to study the impact of errors in conventional arrays, is a valid approximation for superdirective BP statistics only where some mathematical terms are negligible. The paper also shows that this is the case for all linear end-fire arrays considered. A similar study is proposed concerning the correlation between BP lobes, showing that for the superdirective arrays considered the lobes, especially non-adjacent ones, are almost independent. Furthermore, knowledge of the PDF of the actual BP allows one to define quantile BP functions, whose probability of being exceeded, at any point, is fixed. Combining the lobes’ independence with quantile BP functions, an empirical equation for the probability that the entire actual BP will not exceed a quantile function over an interval larger than a given size is obtained. This new knowledge and these tools make it possible to devise new methods to design robust superdirective arrays via optimization goals with clearer and more relevant statistical meaning. [ABSTRACT FROM AUTHOR]

The performance of the recently proposed orientational beamforming (OBF) system for ultra-wideband (UWB) signals degrades seriously in multiuser situation. Although various techniques have been proposed in the literature to suppress multiuser interference in the time-hopping UWB system, there has been no research on interference suppression in the OBF UWB system. In this paper, we propose a nonlinear OBF system via a modified radial basis function (RBF) neural network, named the RBF-OBF system, to reject orientational UWB interferences caused by multiuser transmission in the OBF system. The RBF neural network is selected mainly because of its simple structure, convenient training process, and fast convergence speed. However, the conventional Euclidean-distance-based RBF neural network is not suitable for the training process used in this work, as the training samples are noiseless orientational steering vectors in frequency domain. Therefore, a modified RBF neural network is proposed in this paper, which evaluates the similarity between an input vector and the center vector of a hidden layer neuron by their signed complex correlation coefficient. Numerous simulations demonstrate that compared to the conventional OBF system, the proposed RBF-OBF system can significantly reduce the bit error rates (BERs) under different noise and interference situations. The BER reduction rate of the proposed RBF-OBF system is higher than 92% in additive white Gaussian noise channel and higher than 89% in line-of-sight multipath channel. [ABSTRACT FROM AUTHOR]

The goal of this paper is to investigate linear approximations of random functions and permutations. Our motivation is twofold. First, before the distinguishability of a practical cipher from an ideal one can be analysed, the cryptanalyst must have an accurate understanding of the statistical behaviour of the ideal cipher. Secondly, this issue has been neglected both in old and in more recent studies, particularly when multiple linear approximations are being used simultaneously. Traditional models have been based on the average behaviour and simplified using other assumptions such as independence of the linear approximations. Multidimensional cryptanalysis was introduced to avoid making artificial assumptions about statistical independence of linear approximations. On the other hand, it has the drawback of including many trivial approximations that do not contribute to the attack but just cause a waste of time and memory. We show for the first time in this paper that the trivial approximations reduce the degree of freedom of the related $\chi ^{2}$ distribution. Previously, the affine linear cryptanalysis was proposed to allow removing trivial approximations and, at the same time, admitting a solid statistical model. In this paper, we identify another type of multidimensional linear approximation, called Davies-Meyer approximation, which has similar advantages, and present full statistical models for both the affine and the Davies-Meyer type of multidimensional linear approximations. The new models given in this paper are realistic, accurate and easy to use. They are backed up by standard statistical tools such as Pearson’s $\chi ^{2}$ test and finite population correction and demonstrated to work accurately using practical examples. [ABSTRACT FROM AUTHOR]

A suitable probabilistic scenario set of load demand and natural characteristics of renewable energy is becoming a crucial issue in power system planning studies. Properly addressing the impact of potentially thousands of residential PV plants on the resilience and reliability needs of substations necessitates the representation of inherent relations between photovoltaics and the load throughout the long-term planning period. The optimal planning of substation expansions is achievable through proper modeling of input parameters which describes the characteristics of the service areas. In this paper, the co-existence of PV plants and the load in a service area under three different states such as daytime with clear-sky and no-fault, daytime with abnormal events, and nighttime are incorporated into the stochastic dynamic optimization problem by using scenario-based approach. The scenario tree of the problem is branched from three different bases simultaneously instead of only one as in conventional approach. This paper also combines the risk-constrained stochastic dynamic SEP problem and Mixed Integer Linear Programming (MILP) framework under one roof. The comparison between integrating inherent characteristics of PV plants with and without considering abnormal events into the optimization is performed to show the impact of suitable probabilistic model on dynamic nature of investment decisions. [ABSTRACT FROM AUTHOR]

Low-rank tensor representation philosophy has enjoyed a reputation in many hyperspectral image (HSI) low-level vision applications, but previous studies often failed to comprehensively exploit the low-rank nature of HSI along different modes in low-dimensional subspace, and unsurprisingly handled only one specific task. To address these challenges, in this paper, we figured out that in addition to the spatial correlation, the spectral dependency of HSI also implicitly exists in the coefficient tensor of its subspace, this crucial dependency that was not fully utilized by previous studies yet can be effectively exploited in a cascaded manner. This led us to propose a unified subspace low-rank learning regime with a new tensor cascaded rank minimization, named STCR, to fully couple the low-rankness of HSI in different domains for various low-level vision tasks. Technically, the high-dimensional HSI was first projected into a low-dimensional tensor subspace, then a novel tensor low-cascaded-rank decomposition was designed to collapse the constructed tensor into three core tensors in succession to more thoroughly exploit the correlations in spatial, nonlocal, and spectral modes of the coefficient tensor. Next, difference continuity-regularization was introduced to learn a basis that more closely approximates the HSI’s endmembers. The proposed regime realizes a comprehensive delineation of the self-portrait of HSI tensor. Extensive evaluations conducted with dozens of state-of-the-art (SOTA) baselines on eight datasets verified that the proposed regime is highly effective and robust to typical HSI low-level vision tasks, including denoising, compressive sensing reconstruction, inpainting, and destriping. The source code of our method is released at https://github.com/CX-He/STCR.git. [ABSTRACT FROM AUTHOR]

In multi-label classification, the strategy of label-specific features has been shown to be effective to learn from multi-label examples by accounting for the distinct discriminative properties of each class label. However, most existing approaches exploit the semantic relations among labels as immutable prior knowledge, which may not be appropriate to constrain the learning process of label-specific features. In this paper, we propose to learn label semantics and label-specific features in a collaborative way. Accordingly, a deep neural network (DNN) based approach named Clif, i.e., CollaborativeLearning of label semantIcs and deep label-specificFeatures for multi-label classification, is proposed. By integrating a graph autoencoder for encoding semantic relations in the label space and a tailored feature-disentangling module for extracting label-specific features, Clif is able to employ the learned label semantics to guide mining label-specific features and propagate label-specific discriminative properties to the learning process of the label semantics. In such a way, the learning of label semantics and label-specific features interact and facilitate with each other so that label semantics can provide more accurate guidance to label-specific feature learning. Comprehensive experiments on 14 benchmark data sets show that our approach outperforms other well-established multi-label classification algorithms. [ABSTRACT FROM AUTHOR]

Correspondence analysis (CA) is a multivariate statistical tool used to visualize and interpret data dependencies by finding maximally correlated embeddings of pairs of random variables. CA has found applications in fields ranging from epidemiology to social sciences. However, current methods for CA do not scale to large, high-dimensional datasets. In this paper, we provide a novel interpretation of CA in terms of an information-theoretic quantity called the principal inertia components. We show that estimating the principal inertia components, which consists in solving a functional optimization problem over the space of finite variance functions of two random variable, is equivalent to performing CA. We then leverage this insight to design algorithms to perform CA at scale. Specifically, we demonstrate how the principal inertia components can be reliably approximated from data using deep neural networks. Finally, we show how the maximally correlated embeddings of pairs of random variables in CA further play a central role in several learning problems including multi-view and multi-modal learning methods and visualization of classification boundaries. [ABSTRACT FROM AUTHOR]

In multi-label classification, the strategy of label-specific features has been shown to be effective to learn from multi-label examples by accounting for the distinct discriminative properties of each class label. However, most existing approaches exploit the semantic relations among labels as immutable prior knowledge, which may not be appropriate to constrain the learning process of label-specific features. In this paper, we propose to learn label semantics and label-specific features in a collaborative way. Accordingly, a deep neural network (DNN) based approach named Clif, i.e., CollaborativeLearning of label semantIcs and deep label-specificFeatures for multi-label classification, is proposed. By integrating a graph autoencoder for encoding semantic relations in the label space and a tailored feature-disentangling module for extracting label-specific features, Clif is able to employ the learned label semantics to guide mining label-specific features and propagate label-specific discriminative properties to the learning process of the label semantics. In such a way, the learning of label semantics and label-specific features interact and facilitate with each other so that label semantics can provide more accurate guidance to label-specific feature learning. Comprehensive experiments on 14 benchmark data sets show that our approach outperforms other well-established multi-label classification algorithms. [ABSTRACT FROM AUTHOR]

Correspondence analysis (CA) is a multivariate statistical tool used to visualize and interpret data dependencies by finding maximally correlated embeddings of pairs of random variables. CA has found applications in fields ranging from epidemiology to social sciences. However, current methods for CA do not scale to large, high-dimensional datasets. In this paper, we provide a novel interpretation of CA in terms of an information-theoretic quantity called the principal inertia components. We show that estimating the principal inertia components, which consists in solving a functional optimization problem over the space of finite variance functions of two random variable, is equivalent to performing CA. We then leverage this insight to design algorithms to perform CA at scale. Specifically, we demonstrate how the principal inertia components can be reliably approximated from data using deep neural networks. Finally, we show how the maximally correlated embeddings of pairs of random variables in CA further play a central role in several learning problems including multi-view and multi-modal learning methods and visualization of classification boundaries. [ABSTRACT FROM AUTHOR]

Machine learning research, particularly in genomics, is often based on wide shaped datasets, i.e. datasets having a large number of features, but a small number of samples. Such configurations raise the possibility of chance influence (the increase of measured accuracy due to chance correlations) on the learning process and the evaluation results. Prior research underlined the problem of generalization of models obtained based on such data. In this paper, we investigate the influence of chance on prediction and show its significant effects on wide shaped datasets. First, we empirically demonstrate how significant the influence of chance in such datasets is by showing that prediction models trained on thousands of randomly generated datasets can achieve high accuracy. This is the case even when using cross-validation. We then provide a formal analysis of chance influence and design formal chance influence estimators based on the dataset parameters, namely its sample size, the number of features, the number of classes and the class distribution. Finally, we provide an in-depth discussion of the formal analysis including applications of the findings and recommendations on chance influence mitigation. [ABSTRACT FROM AUTHOR]

Currently, electroencephalogram (EEG) is mostly analyzed in a supervised way, which requires EEG labels (e.g., EEG classification). With the ever-increasing amount of unlabeled/mislabeled EEG in neuropsychiatric disorder diagnosis, BCI, and rehabilitation, manually labeling of EEG data is a labor intensive and time-consuming process, and few labs have developed algorithms to analyze EEG in an unsupervised manner (i.e., EEG clustering). In this paper, we propose a cooperative game inspired approach to cluster multi-trial EEG data. The idea is to map multi-trial EEG clustering to the coalition formation in a cooperative game, and then identify cluster center (the EEG trial with highest Shapley value) and assign EEG trials into proper clusters based on their cross correlation-transformed Shapley values. We demonstrate the mapped EEG cooperative game is convex, and it leads to an algorithm for multi-trial EEG clustering named CoGEEGc. The CoGEEGc yields high-quality multi-trial EEG clustering with respect to intra-cluster compactness and inter-cluster scatter. We show that CoGEEGc outperforms 15 state-of-the-art EEG or time series clustering approaches through detailed experimentation on real-world multi-trial EEG datasets. Comparison against 15 methods with four theoretical properties of clustering further illustrates the superiority of CoGEEGc, as it satisfies two properties while other approaches only satisfy one. [ABSTRACT FROM AUTHOR]

Pathology analysis is crucial to precise cancer diagnoses and the succeeding treatment plan as well. To detect abnormality in histopathology images with prevailing patch-based convolutional neural networks (CNNs), contextual information often serves as a powerful cue. However, as whole-slide images (WSIs) are characterized by intense morphological heterogeneity and extensive tissue scale, a straightforward visual span to a larger context may not well capture the information closely associated with the focal patch. In this paper, we propose a novel pixel-offset based patch-location method to identify high-representative tissues, with a CNN backbone. Pathology Deformable Conditional Random Field (PDCRF) is proposed to learn the offsets and weights of neighboring contexts in a spatial-adaptive manner, to search for high-representative patches. A CNN structure with the localized patches as training input is then capable of consistently reaching superior classification outcomes for histology images. Overall, the proposed method has achieved state-of-the-art performance, in terms of the test classification accuracy improvement to the baseline by 1.15-2.60%, 0.78-1.78%, and 1.47-2.18% on TCGA public datasets of TCGA-STAD, TCGA-COAD, and TCGA-READ respectively. It also achieves 88.95% test accuracy and 0.920 test AUC on Camelyon 16. To show the effectiveness of the proposed framework on downstream tasks, we take a further step by incorporating an active learning model, which noticeably reduces the number of manual annotations by PDCRF to reach a parallel patch-based histology classifier. [ABSTRACT FROM AUTHOR]

The notion of correlation immune functions has been introduced by Siegenthaler (1984) in symmetric cryptography in the framework of stream ciphers. At the conference CRYPTO’91 by Camion et al., it has been pointed out that this notion existed in statistics and combinatorics. It has recently been highlighted that such functions also play an important role in a new framework related to side-channel attack counter-measures. Since then, the interest in correlation immune Boolean functions has been renewed, and new challenges regarding these functions have appeared. Specifically, low Hamming weight correlation immune functions have been selected as useful for counter-measures to side-channel attacks. Despite their importance, the literature is not abundant in this research direction. Two very interesting articles in which such correlation immune functions were nicely explored, given this novel use of them. Carlet initiated the first one in 2013, and the second one is due to Carlet and Chen (2018). This paper deals with correlation immune Boolean functions aiming to produce more candidates of those processing low Hamming weights. We shall focus on correlation immune Boolean functions with Hamming weights power of 2 (which offer a flexibility to control the correlation immunity aspects) and present several methods of designing them. Some design methods are efficient and could be employed to derive such functions. Consequently, given two positive integers $n$ and $m$ , we derive new effective constructions of correlation immune Boolean functions with Hamming weight power of 2. Furthermore, an upper bound on the correlation immunity of the newly constructed $n$ -variable Boolean functions with Hamming weight $2^{m}$ was determined for $n-m\ge 0$. Besides, exact values and lower bounds on the maximum correlation immunity of those functions are explored and discussed, mainly when the values of $n$ and $m$ are very close. This paper also exhibits explicit examples of those correlation immune functions that illustrate our methods. [ABSTRACT FROM AUTHOR]

This paper proposes a systematic and general approach to model correlated stochastic processes in power systems by means of stochastic differential-algebraic equations. The paper discusses the theoretical background of stochastic differential-algebraic equations and provides a variety of examples of correlated stochastic models for power system applications. With this aim, stochastic processes with Normal and Weibull distributions are considered. The case study utilizes the well-known two-area system to demonstrate that the presence of correlation between the stochastic processes can cause instability, despite the fact that the same system is stable if the same processes are uncorrelated. The case study also considers a 1479-bus dynamic model of the all-island Irish transmission system to show the scalability of the proposed technique, and to compare scenarios with different levels of correlation among stochastic processes. Results indicate that correlation has a non-negligible impact on short-term dynamics. A high level of correlation among the processes, in fact, can give raise to instability. [ABSTRACT FROM AUTHOR]

In steady-state visual-evoked potential (SSVEP) based brain-computer interfaces (BCIs), existing detection algorithms utilizing spatial filters like task-related component analysis (TRCA) derive the spatial filters mainly through maximizing the inter-trial similarity between the combined signals over the training set. Although they achieve by far the best classification performance in SSVEP-based BCIs, some important problems are still unresolved. Especially, the mechanism of how spatial filters cancel the background noise in brain signals and optimize the signal-to-noise ratio (SNR) of SSVEPs is still not figured out. Therefore, to solve these problems, in this paper a new perspective of spatial filter design is proposed. Specifically, a linear generative signal model of SSVEP is adopted and the spatial filters are obtained automatically through maximum likelihood estimation of source signals and channel vectors. In the same time, the relation between maximum likelihood estimation and signal-to-noise ratio (SNR) maximization is discussed. Through a step-by-step formulation, this paper provides a theoretical justification for those conventional algorithms utilizing spatial filters. As for the classification performance, the proposed scheme is tested on a benchmark dataset of 35 subjects. Experiment results show that the classification performance of the proposed scheme is competitive against three benchmark algorithms, which include TRCA. Especially, the proposed scheme achieves a fair performance improvement over the benchmark methods in the cases where a shorter time window, or a larger number of electrodes, or a smaller number of training blocks are adopted. [ABSTRACT FROM AUTHOR]

At present, in the suspension system of maglev train, the self-diagnosis of most of the components can be realized employing direct sensor measurement, however, there are still some components that cannot be directly measured by sensors or model-based methods, such as the power components in the suspension control box, electromagnetics and related connectors. And although the detection method based on Stable Kernel Representation (SKR) can detect the fault, the length of the data used for SKR affects the speed and results of the detection. To obtain better detection results with the shortest possible data, this paper studies a component-level fault detection method based on autocorrelation length and SKR. This method uses the autocorrelation length to determine the length of the data used to identify the SKR, and then applies the SKR to build a residual generator and set the residual threshold. The experimental results show that the studied method can detect faults of the suspension control box in real-time and effectively, and the simulation results show that the studied method can detect faults of the electromagnet in real-time and effectively. In addition, compared with the traditional method, the method in this paper can obtain better results with less data. [ABSTRACT FROM AUTHOR]

Scene flow represents the 3D motion of every point in the dynamic environments. Like the optical flow that represents the motion of pixels in 2D images, 3D motion representation of scene flow benefits many applications, such as autonomous driving and service robot. This paper studies the problem of scene flow estimation from two consecutive 3D point clouds. In this paper, a novel hierarchical neural network with double attention is proposed for learning the correlation of point features in adjacent frames and refining scene flow from coarse to fine layer by layer. The proposed network has a new more-for-less hierarchical architecture. The more-for-less means that the number of input points is greater than the number of output points for scene flow estimation, which brings more input information and balances the precision and resource consumption. In this hierarchical architecture, scene flow of different levels is generated and supervised respectively. A novel attentive embedding module is introduced to aggregate the features of adjacent points using a double attention method in a patch-to-patch manner. The proper layers for flow embedding and flow supervision are carefully considered in our network designment. Experiments show that the proposed network outperforms the state-of-the-art performance of 3D scene flow estimation on the FlyingThings3D and KITTI Scene Flow 2015 datasets. We also apply the proposed network to the realistic LiDAR odometry task, which is a key problem in autonomous driving. The experiment results demonstrate that our proposed network can outperform the ICP-based method and shows good practical application ability. The source codes will be released on https://github.com/IRMVLab/HALFlow. [ABSTRACT FROM AUTHOR]

One objective of this paper is to propose a novel class of sequence pairs, called “quasi-orthogonal Z-complementary pairs (QOZCPs)”, each depicting Z-complementary property for their aperiodic auto-correlation sums and also having a low correlation zone when their aperiodic cross-correlation is considered. Construction of QOZCPs based on Successively Distributed Algorithms under Majorization Minimization (SDAMM) is presented. Another objective of this paper is to apply the proposed QOZCPs in fully polarimetric radar systems and analyse the corresponding ambiguity functions. It turns out that QOZCP waveforms are much more Doppler resilient than the known Golay complementary waveforms. [ABSTRACT FROM AUTHOR]

Let m be an even positive integer. A Boolean bent function ƒ on F2m-1 × F2 is called a cyclic bent function if for any a ≠ b ∈ F2m-1 and ε ∈ F2, ƒ(ax1, x2)+ ƒ(bx1, x2 + ε) is always bent, where x1 ∈ F2m-1, x2 ∈ F2. Cyclic bent functions look extremely rare. This paper focuses on cyclic bent functions on F2m-1 × F2 and their applications. The first objective of this paper is to establish a link between quadratic cyclic bent functions and a special type of prequasifields, and construct a class of quadratic cyclic bent functions from the Kantor-Williams prequasifields. The second objective is to use cyclic bent functions to construct families of optimal sequences. The results of this paper show that cyclic bent functions have nice applications in several fields such as coding theory, symmetric cryptography, and CDMA communication. [ABSTRACT FROM AUTHOR]

Semantic parsing, edge detection, and pose estimation of human are three closely-related tasks. They present human characteristics from three complementary aspects. Compared to learning them individually, solving these tasks jointly can explore the interaction of their contextual cues. However, prior works usually study the fusion of two of them, e.g., parsing and pose, parsing and edge. In this paper, we explore how pixel-level semantics, human boundaries and joint locations can be effectively learned in a unified model. Specifically, we propose an end-to-end trainable Human Task Correlation Machine (HTCorrM) to implement the three tasks. It is asymmetric in that it supports a main task using the other two as auxiliary tasks. We also introduce a Heterogeneous Non-Local module (HNL) to discover the correlations of the three heterogeneous domains. HNL fully explores the global dependency among tasks between any two positions in the feature map. Experimental results on human parsing, pose estimation and body edge detection demonstrate that HTCorrM achieves competitive performance. We show that when designated as the main task, the accuracy of each of the three tasks is improved. Importantly, comparative studies confirm the advantages of our proposed feature correlation strategy over feature concatenation or post processing. [ABSTRACT FROM AUTHOR]

Channel attention mechanisms have been commonly applied in many visual tasks for effective performance improvement. It is able to reinforce the informative channels as well as to suppress the useless channels. Recently, different channel attention modules have been proposed and implemented in various ways. Generally speaking, they are mainly based on convolution and pooling operations. In this paper, we propose Gaussian process embedded channel attention (GPCA) module and further interpret the channel attention schemes in a probabilistic way. The GPCA module intends to model the correlations among the channels, which are assumed to be captured by beta distributed variables. As the beta distribution cannot be integrated into the end-to-end training of convolutional neural networks (CNNs) with a mathematically tractable solution, we utilize an approximation of the beta distribution to solve this problem. To specify, we adapt a Sigmoid-Gaussian approximation, in which the Gaussian distributed variables are transferred into the interval [0,1]. The Gaussian process is then utilized to model the correlations among different channels. In this case, a mathematically tractable solution is derived. The GPCA module can be efficiently implemented and integrated into the end-to-end training of the CNNs. Experimental results demonstrate the promising performance of the proposed GPCA module. Codes are available at https://github.com/PRIS-CV/GPCA. [ABSTRACT FROM AUTHOR]

Accurate traffic forecasting is critical in improving safety, stability, and efficiency of intelligent transportation systems. Despite years of studies, accurate traffic prediction still faces the following challenges, including modeling the dynamics of traffic data along both temporal and spatial dimensions, and capturing the periodicity and the spatial heterogeneity of traffic data, and the problem is more difficult for long-term forecast. In this paper, we propose an Attention based Spatial-Temporal Graph Neural Network (ASTGNN) for traffic forecasting. Specifically, in the temporal dimension, we design a novel self-attention mechanism that is capable of utilizing the local context, which is specialized for numerical sequence representation transformation. It enables our prediction model to capture the temporal dynamics of traffic data and to enjoy global receptive fields that is beneficial for long-term forecast. In the spatial dimension, we develop a dynamic graph convolution module, employing self-attention to capture the spatial correlations in a dynamic manner. Furthermore, we explicitly model the periodicity and capture the spatial heterogeneity through embedding modules. Experiments on five real-world traffic flow datasets demonstrate that ASTGNN outperforms the state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

Predicting treatment medicines is a key task in many intelligent healthcare systems. Prediction of treatment medicines can assist doctors in making informed prescription decisions for patients according to their Electronic Health Records (EHRs). However, predicting treatment medicines is a challenging task due to the following reasons: (1) heterogeneous nature of EHR data that typically includes laboratory results, treatment records, disease conditions, and demographic information; (2) complex correlations among EHR sequences, including inter-correlations between sequences and temporal intra-correlations within each sequence; (3) temporal dynamics of these correlations changing with disease progression. In this paper, we predict treatment medicines for patients with dual adaptive sequential networks (DASNet). Specifically, DASNet is designed with three components. First, a decomposed adaptive long short-term memory network (DA-LSTM) is designed to capture the intra- and inter-correlations in multiple heterogeneous temporal sequences. Then, we develop an attentive meta learning network (AT-MetaNet) to learn dynamic weight parameters for DA-LSTM, thus enabling it to model various correlation structures. Finally, we employ an attentive fusion network (AT-FuNet) to incorporate historical information and collectively fuse representation embeddings of heterogeneous data to predict treatment medicines. Our results on the public MIMIC-III dataset covering 11 medical conditions demonstrate that the proposed end-to-end model can achieve the state-of-the-art prediction performance while providing clinically useful insights. [ABSTRACT FROM AUTHOR]

The most commonly used setting in the coded caching literature consists of the following four elements: (i) homogeneous file sizes, (ii) homogeneous cache sizes, (iii) user-independent homogeneous file popularity (i.e., all users share the same file preference), and (iv) worst-case rate analysis. While recent results have relaxed some of these assumptions, deeper understanding of the full heterogeneity setting is still much needed since traditional caching schemes place little assumptions on file/cache sizes and almost always allow each user to have his/her own file preference through individualized file request prediction. Taking a microscopic approach, this paper characterizes the exact capacity of the smallest 2-user/2-file ($N=K=2$) problem but under the most general setting that simultaneously allows for (i) heterogeneous files sizes, (ii) heterogeneous cache sizes, (iii) user-dependent file popularity, and (iv) average-rate analysis. Solving completely the case of $N=K=2$ could shed further insights on the performance and complexity of optimal coded caching with full heterogeneity for arbitrary $N$ and $K$. [ABSTRACT FROM AUTHOR]

As the network slicing is one of the critical enablers in communication networks, one anomalous physical node (PN) or physical link (PL) in substrate networks that carries multiple virtual network elements can cause significant performance degradation of multiple network slices. To recover the substrate networks from anomaly within a short time, rapid and accurate identification of whether or not the anomaly exists in PNs and PLs is vital. Online anomaly detection methods that can analyze system data in real-time are preferred. Besides, as virtual nodes and links mapped to PNs and PLs are scattered in multiple slices, the distributed detection modes are required to adapt to the virtualized environment. According to those requirements, in this paper, we first propose a distributed online PN anomaly detection algorithm based on a decentralized one-class support vector machine (OCSVM), which is realized through analyzing real-time measurements of virtual nodes mapped to PNs in a distributed manner. Specifically, to decouple the OCSVM objective function, we transform the original problem to a group of decentralized quadratic programming problems by introducing the consensus constraints. The alternating direction method of multipliers is adopted to achieve the solution for the distributed online PN anomaly detection. Next, by utilizing the correlation of measurements between neighbor virtual nodes, another distributed online PL anomaly detection algorithm based on the canonical correlation analysis is proposed. The network only needs to store covariance matrices and mean vectors of current data to calculate the canonical correlation vectors for real-time PL anomaly analysis. The simulation results on both synthetic and real-world network datasets show the effectiveness and robustness of the proposed distributed online anomaly detection algorithms. [ABSTRACT FROM AUTHOR]

An electromagnetic map (EM) can provide movable base stations with information to optimize the communication quality of temporary communication systems in disaster areas, such as areas suffering from earthquakes. In this paper, a low-cost and effective communication optimization system model that uses sensing nodes and EMs is proposed. Moreover, two EM reconstruction methods, which serve as the keys to the model, are proposed to reconstruct EMs to provide information for communication optimization according to different demands. One method is KGA-GAN-SBI, which combines the kriging algorithm, generative adversarial network and split bregman iterations, and the other is APCA-KGA-DPA, which combines the affinity propagation clustering algorithm, kriging algorithm and domain mapping algorithm. The former can satisfy the demand of high-accuracy EMs. The latter can reconstruct an EM faster than KGA-GAN-SBI. The simulation results show that both low-cost methods can reconstruct more accurate EMs than several existing algorithms; they can provide an effective way to optimize the communication quality of temporary communication and fill the gap in the study of EM applications. [ABSTRACT FROM AUTHOR]

Correlation filters with Convolutional Neural Networks (CNNs) features have obtained tremendous attention and success in visual tracking. However, redundant and noisy feature channels existed in CNN features may cause severe over-fitting and greatly limit the discriminative power of the tracking model. To tackle the issue, in this paper, we develop a new and effective channel-aware correlation filters (CACF) method for boosting the tracking performance. Our CACF method aims to dynamically select representative and discriminative feature channels from high-dimensional CNN features to reduce the model complexity and better distinguish the target object from the background. Moreover, the CACF model is solved by the alternating direction method of multipliers (ADMM) to learn correlation filters. By retaining reliable feature channels, our CACF tracking method can reach better generalization ability and discriminative ability to accurately localize the target object. Comprehensive experiments are conducted on challenging tracking datasets, and the experiment results prove that our CACF method obtains favorable tracking accuracy compared to several popular tracking methods. [ABSTRACT FROM AUTHOR]

Event popularity prediction over social media is crucial for estimating information propagation scope, decision making, and emergency prevention. However, existing approaches only focus on predicting the occurrences of single attribute such as a message, a hashtag or an image, which are not comprehensive enough for representing complex social event propagation. In this paper, we predict the event popularity, where an event is described as a set of messages containing multiple hashtags. We propose a novel hashtag-influence-based event popularity prediction by mining the impact of an influential hashtag set on the event propagation. Specifically, we first propose a hashtag-influence-based cascade model to select the influential hashtags over an event hashtag graph built by the pairwise hashtag similarity and the topic distribution of event-related hashtags. A novel measurement is proposed to identify the hashtag influence of an event over its content and social impacts. A hashtag correlation-based algorithm is proposed to optimize the seed selection in a greedy manner. Then, we propose an event-fitting boosting model to predict the event popularity by embedding the feature importance over events into the XGBOOST model. Moreover, we propose an event-structure-based method, which incrementally updates the prediction model over social streams. We have conducted extensive experiments to prove the effectiveness and efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

Let $\mathbf {X}\in \mathbb {C}^{n\times m}$ ($m\geq n$) be a random matrix with independent columns each distributed as complex multivariate Gaussian with zero mean and single-spiked covariance matrix $\mathbf {I}_{n}+ \eta \mathbf {u}\mathbf {u}^{*}$ , where $\mathbf {I}_{n}$ is the $n\times n$ identity matrix, $\mathbf {u}\in \mathbb {C}^{n\times 1}$ is an arbitrary vector with unit Euclidean norm, $\eta \geq 0$ is a non-random parameter, and $(\cdot)^{*}$ represents the conjugate-transpose. This paper investigates the distribution of the random quantity $\kappa _{\text {SC}}^{2}(\mathbf {X})=\sum _{k=1}^{n} \lambda _{k}/\lambda _{1}$ , where $0\le \lambda _{1}\le \lambda _{2}\le \ldots \leq \lambda _{n} < \infty $ are the ordered eigenvalues of $\mathbf {X}\mathbf {X}^{*}$ (i.e., single-spiked Wishart matrix). This random quantity is intimately related to the so called scaled condition number or the Demmel condition number (i.e., $\kappa _{\text {SC}}(\mathbf {X})$) and the minimum eigenvalue of the fixed trace Wishart-Laguerre ensemble (i.e., $\kappa _{\text {SC}}^{-2}(\mathbf {X})$). In particular, we use an orthogonal polynomial approach to derive an exact expression for the probability density function of $\kappa _{\text {SC}}^{2}(\mathbf {X})$ which is amenable to asymptotic analysis as matrix dimensions grow large. Our asymptotic results reveal that, as $m,n\to \infty $ such that $m-n$ is fixed and when $\eta $ scales on the order of $1/n$ , $\kappa _{\text {SC}}^{2}(\mathbf {X})$ scales on the order of $n^{3}$. In this respect we establish simple closed-form expressions for the limiting distributions. It turns out that, as $m,n\to \infty $ such that $n/m\to c\in (0,1)$ , properly centered $\kappa _{\text {SC}}^{2}(\mathbf {X})$ fluctuates on the scale $m^{\frac {1}{3}}$. [ABSTRACT FROM AUTHOR]

Pedestrian attribute recognition (PAR), which aims to identify attributes of the pedestrians captured in video surveillance, is a challenging task due to the poor quality of images and diverse spatial distribution among attributes. Existing methods usually model PAR as a multi-label classification problem and manually map attributes to an ordered list corresponding to the outputs of classifiers or sequential models. However, the inherent textual information among attribute annotations is largely neglected in these visual-only methods. In this paper, we first alleviate this issue by proposing a novel visual-textual baseline (VTB) for PAR which introduces an additional textual modality to explore the textual semantic correlations from attribute annotations by pre-trained textual encoders instead of human definitions. VTB encodes pedestrian images and attribute annotations into visual and textual features respectively, interacts with information across modalities, and predicts recognition results independently to remove the influence of attribute orders. Furthermore, we introduce transformer encoder as the cross-modal fusion module in VTB for sufficient intra-modal and cross-modal correlations exploration. Our method achieves superior performance over most existing visual-only methods on two widely used datasets including RAP and PA-100K, demonstrating the effectiveness of utilizing textual modality to PAR. Our method is expected to serve as a multimodal PAR baseline and inspire new insights for multimodal fusion in future PAR research. Our code is available at https://github.com/cxh0519/VTB. [ABSTRACT FROM AUTHOR]

Gait recognition can be used in person identification and re-identification by itself or in conjunction with other biometrics. Although gait has both spatial and temporal attributes, and it has been observed that decoupling spatial feature and temporal feature can better exploit the gait feature on the fine-grained level. However, the spatial-temporal correlations of gait video signals are also lost in the decoupling process. Direct 3D convolution approaches can retain such correlations, but they also introduce unnecessary interferences. Instead of common 3D convolution solutions, this paper proposes an integration of decoupling process into a 3D convolution framework for cross-view gait recognition. In particular, a novel block consisting of a Parallel-insight Convolution layer integrated with a Spatial-Temporal Dual-Attention (STDA) unit is proposed as the basic block for global spatial-temporal information extraction. Under the guidance of the STDA unit, this block can well integrate spatial-temporal information extracted by two decoupled models and at the same time retain the spatial-temporal correlations. In addition, a Multi-Scale Salient Feature Extractor is proposed to further exploit the fine-grained features through context awareness extension of part-based features and adaptively aggregating the spatial features. Extensive experiments on three popular gait datasets, namely CASIA-B, OULP and OUMVLP, demonstrate that the proposed method outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Video saliency prediction (VSP) aims to imitate eye fixations of humans. However, the potential of this task has not been fully exploited since existing VSP methods only focus on modeling visual saliency of the input previous frames. In this paper, we present the first attempt to extend this task to video saliency forecasting (VSF) by forecasting attention regions of consecutive future frames. To tackle this problem, we propose a video saliency forecasting transformer (VSFT) network built on a new encoder-decoder architecture. Different from existing VSP methods, our VSFT is the first pure-transformer based architecture in the VSP field and is freed from the dependency of the pretrained S3D model. In VSFT, the attention mechanism is exploited to capture spatial-temporal dependencies between the input past frames and the target future frame. We propose cross-attention guidance blocks (CAGB) to aggregate multi-level representation features to provide sufficient guidance for forecasting. We conduct comprehensive experiments on two benchmark datasets, DHF1K and Hollywoods-2. We investigate the saliency forecasting and predicting abilities of existing VSP methods by modifying the supervision signals. Experimental results demonstrate that our method achieves superior performance on both VSF and VSP tasks. [ABSTRACT FROM AUTHOR]

Reversible data hiding in encrypted images (RDHEI), an essential branch of reversible data hiding (RDH), has been in development for more than a decade. For most existing stream-cipher-based RDHEI algorithms, encryption schemes are often not the same; thus, these schemes have different effects on the encrypted images. As a result, it is not reasonable to compare the embedding rates (ERs) of RDHEI algorithms directly as we do for plaintext RDH algorithms. However, to our knowledge, many studies focus on the performance of embedding but neglect the influence of the encryption. To compare the performance of stream-cipher-based RDHEI algorithms more reasonably, this paper proposes a novel comprehensive measure to evaluate state-of-the-art RDHEI algorithms. First, the characteristics of the stream-cipher-based RDHEI algorithms are divided into two categories according to the encryption and embedding processes. Next, we use correlation and redundancy to evaluate the influence of encryption schemes and also use ER, computation complexity, visual quality, and algorithm stability to evaluate the embedding schemes. In the end, in order to combine all six indexes into the final evaluation measure, we standardize each index before applying the radar chart. The experimental results show the evaluation results of the recent RDHEI algorithms via a comprehensive analysis and demonstrate the guiding significance of the proposed method for the current RDHEI algorithm selection. [ABSTRACT FROM AUTHOR]

Crowd counting is a task of intelligent applications, and its operation efficiency is very important. However, in order to obtain a better counting performance, most of the existing works often design larger and more complex network structures, which will result in them occupying considerable memory, time and other resources at runtime, seriously limiting their deployment scope and making it difficult to be widely used in practical scenarios. In this paper, in order to overcome the above problems, we propose an effective lightweight encoding-decoding crowd counting network, named Lw-Count. Specifically, in the encoding process, we design an efficient and lightweight convolution module (ELCM), which extracts the crowd features in the network through a refined ghost block to reduce the network parameters and computing cost, and solves the problem of inaccurate counting caused by uneven crowd distribution through spatial group normalization (SGN). In the decoding process, we design a scale regression module (SRM) to reduce the error details and chessboard effect caused by linear interpolation and deconvolution. In addition, we design a new loss function, which enhances the spatial correlation of the density map and the sensitivity of the crowd through a regional normalized cross-correlation loss and counting loss, to ensure the counting accuracy. Extensive experiments on five mainstream datasets demonstrate that Lw-Count achieves an optimal trade-off between counting performance and running speed compared with other methods. [ABSTRACT FROM AUTHOR]

Pruning can remove the redundant parameters and structures of Deep Neural Networks (DNNs) to reduce inference time and memory overhead. As one of the important components of DNN, feature maps (FMs) have been widely used in network pruning. However, previous approaches do not fully investigate the discriminative features in FMs, and also do not explicitly utilize all the features associated with each layer in the pruning procedure. In this paper, we explore the discriminative feature of FMs and explicitly investigate the two-adjacent-layer features of each layer to propose a three-phase hierarchical pruning framework, dubbed as FCHP. Firstly, we decompose each FM into several components to extract the discriminative feature. After that, since pruning each layer is related to the FMs of adjacent layers, we explicitly calculate the feature correlation of discriminative features of two adjacent layers, and then use the feature correlation to cluster FMs into several hierarchies to guide subsequent pruning. Finally, we compute the content of discriminative features, and remove channels corresponding to FMs with fewer discriminative features in each hierarchy, respectively. In the experiment, we prune DNNs with the multiple types of architecture on different benchmarks, and the results have achieved the state-of-the-arts in terms of compressed parameters and FLOPs drop. For example, as for ResNet-56 on CIFAR-10, FCHP respectively obtains 50% of parameters and FLOPs reduction with negligible accuracy loss. Besides, as for ResNet-50 on ImageNet, FCHP reduces 40.5% of parameters and 44.1% of FLOPs with 0.43% of Top-1 accuracy drop. [ABSTRACT FROM AUTHOR]

Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current research on video attention generally focuses on adopting a specific aspect of contexts (e.g., channel, spatial/temporal, or global context) to refine the features and neglects their underlying correlation when computing attentions. This leads to incomplete context utilization and hence bears the weakness of limited performance improvement. To tackle the problem, this paper proposes an efficient attention-in-attention (AIA) method for element-wise feature refinement, which investigates the feasibility of inserting the channel context into the spatio-temporal attention learning module, referred to as CinST, and also its reverse variant, referred to as STinC. Specifically, we instantiate the video feature contexts as dynamics aggregated along a specific axis with global average and max pooling operations. The workflow of an AIA module is that the first attention block uses one kind of context information to guide the gating weights calculation of the second attention that targets at the other context. Moreover, all the computational operations in attention units act on the pooled dimension, which results in quite few computational cost increase (< 0.02%). To verify our method, we densely integrate it into two classical video network backbones and conduct extensive experiments on several standard video classification benchmarks. The source code of our AIA is available at https://github.com/haoyanbin918/Attention-in-Attention. [ABSTRACT FROM AUTHOR]

It is found from actual data that due to generation dispatch and uncertain renewable generations and loads with complicated correlations, inferring the probabilistic distributions for uncertain inputs is challenging. Many probabilistic power flow approaches have been developed in the literature but their validations using realistic systems and data are lacking. This paper proposes a data-driven probabilistic analysis approach for system risk assessment of the miniWECC system using actual data. The sparse Gaussian process (SGP) is advocated to quantify the impacts of uncertain inputs on voltage security. SGP does not need the probability distribution function of uncertain inputs, can handle correlations and is highly computationally efficient. Results on the miniWECC system using realistic data show that SGP outperforms existing approaches and is able to quantify the voltage violation risks. [ABSTRACT FROM AUTHOR]