Search

Multivariate time series usually have entangled temporal patterns and various anomaly types. Meanwhile, they often contain both continuous and discrete features. Many existing methods directly model correlations in complex multivariate time series to conduct anomaly detection. Decomposing time series into different components, such as the overall trend and fluctuations, can contribute to better extracting semantic information and detecting anomalies. Existing decomposition-based anomaly detection methods still have several limitations. First, they directly decompose all features without considering that discrete features are unsuitable for decomposition because they do not have trends or fluctuations. Second, they adopt the same networks for different components with different characteristics, limiting their ability to extract semantic information. Moreover, due to the nature of Transformers, existing reconstruction-based methods using Transformers rarely form information bottlenecks, reducing the differentiation between the reconstruction errors of normal data and anomalies. This paper proposes a multivariate time series anomaly detection method with separation, decomposition, and dual Transformer-based autoencoder (SDDformer). Different from existing methods, SDDformer separates continuous and discrete features and only decomposes continuous features into trend and residual components. Considering the different characteristics of different components, SDDformer adopts Crossformer and the vanilla Transformer as the backbone of two different autoencoders to reconstruct the trend and residual components. Information bottlenecks are better formed using an extra token as the latent variable between the encoder and the decoder. SDDformer regards reconstructing a discrete feature as a classification task and calculates Cross-Entropy as its reconstruction error. Three different metrics are adopted in this paper to compare SDDformer with a variety of typical anomaly detection methods on public data sets, and the experimental results prove that SDDformer can achieve state-of-the-art performance. • A two-stream multivariate time series anomaly detection method is proposed. • Continuous and discrete features are separated before decomposition. • Only continuous features are decomposed into the trend and residual components. • Two different autoencoders are proposed to reconstruct different components. • The reconstruction of a discrete feature is regarded as a classification task. [ABSTRACT FROM AUTHOR]

In this paper we show that the largest possible size of a subset of F q n avoiding right angles, that is, distinct vectors x , y , z such that x − z and y − z are perpendicular to each other is at most O (n q − 2). This improves on the previously best known bound due to Naslund [13] and refutes a conjecture of Ge and Shangguan [11]. A lower bound of n q / 3 is also presented. It is also shown that a subset of F q n avoiding triangles with all right angles can have size at most O (n 2 q − 2). Furthermore, asymptotically tight bounds are given for the largest possible size of a subset A ⊆ F q n for which x − y is not self-orthogonal for any distinct x , y ∈ A. The exact answer is determined for q = 3 and n ≡ 2 (mod 3). Our methods can also be used to bound the maximum possible size of a binary code where no two codewords have Hamming distance divisible by a fixed prime q. Our lower- and upper bounds are asymptotically tight and both are sharp in infinitely many cases. [ABSTRACT FROM AUTHOR]

• GML (Group Meta-Learning) is proposed to effectively alleviate the problem that low-quality samples have unfavourable impact on the training effect under few-shot conditions, thereby improving the performance of the model. • Momentum update strategy is introduced to few-shot learning for the first time to effectively improve the generalization and stability of the model, and an adaptive momentum coefficient is designed to form AMS (Adaptive Momentum Smoothing) to further improve the training efficiency. • We propose MGML (Momentum Group Meta-Learning) by combining GML and AMS. MGML not only improves the accuracy of Meta-Learning Baseline, but also has good mobility. It can be inserted into previous state-of-the-art methods and get consistent performance improvements. At present, image classification covers more and more fields, and it is often difficult to obtain enough data for learning in some specific scenarios, such as medical fields, personalized customization of robots, etc. Few-shot image classification aims to quickly learn new classes of features from few images, and the meta-learning method has become the mainstream due to its good performance. However, the generalization ability of the meta-learning method is still poor and easy to be disturbed by low-quality images. In order to solve the above problems, this paper proposes Momentum Group Meta-Learning (MGML) to achieve a better effect of few-shot learning, which contains Group Meta-Learning module (GML) and Adaptive Momentum Smoothing module (AMS). GML obtains an ensemble model by training multiple episodes in parallel and then grouping them, which can reduce the interference of low-quality samples and improve the stability of meta-learning training. AMS includes the adaptive momentum update rule to further optimally integrate models between different groups, so that the model can memorize experience in more scenarios and enhance the generalization ability. We conduct experiments on miniImageNet and tieredImageNet datasets. The results show that MGML improves the accuracy, stability and cross-domain transfer ability of few-shot image classification, and can be applied to different few-shot learning models. [ABSTRACT FROM AUTHOR]

How to efficiently represent a graph in computer memory is a fundamental data structuring question. In the present paper, we address this question from a combinatorial point of view. A representation of an n -vertex graph G is called implicit if it assigns to each vertex of G a binary code of length O (log ⁡ n) so that the adjacency of two vertices is a function of their codes. A necessary condition for a hereditary class X of graphs to admit an implicit representation is that X has at most factorial speed of growth. This condition, however, is not sufficient, as was recently shown in [19]. Several sufficient conditions for the existence of implicit representations deal with boundedness of some parameters, such as degeneracy or clique-width. In the present paper, we analyze more graph parameters and prove a number of new results related to implicit representation and factorial properties. [ABSTRACT FROM AUTHOR]

Hashing technology can support large-scale recommendation very effectively due to its advantages of low storage cost and high recommendation efficiency. However, existing hashing-based recommendation methods often suffer from item cold-start problem. This is because they simply consider the user-item interaction and the single content information of the items, but the full interaction history is not always available and the single auxiliary information may be missing. To solve this issue, in this paper we propose a Binary Multi-modal Matrix Factorization (BMMF) method. First, we propose an efficient consensus multi-modal mapping to transform the heterogeneous multi-modal features to the unified factors by exploiting the complementarity of multiple modalities. Then, binary matrix factorization is simultaneously performed on the multi-modal features of the items and past user preferences to learn the compact binary codes of the users/items in a common Hamming space. In addition, inspired by the observation that similar instances often have similar binary codes within a short Hamming distance, we formulate a semantic structure regularization term to preserve the similarities of the items during the binary embedding process. Finally, we develop an effective Discrete Coordinate Descent (DCD) approach to tackle the formulated discrete hash optimization problem directly. Experiments on three publicly available real-world datasets demonstrate the superiority of the proposed method against the state-of-the-art methods. Our source codes and testing datasets are available at https://github.com/pcm1217/BMMF. [ABSTRACT FROM AUTHOR]

Many structural models in chemistry, biology, computer science, sociology, and operations research can be analyzed using graph theory. Some examples of these structure models are species movement between regions, molecular bonds, shortest spanning trees, development of computer algorithms. This paper introduces the edge decomposition of circulant graphs with 2 n vertices by different graph classes. These circulant graphs are denoted as C 2 n , n , where n is the degree of the graph C 2 n , n. We propose two algorithmic approaches for constructing edge decomposition of C 2 n , n. With aid of the proposed algorithmic approaches, we construct paths decompositions, trees decompositions, disjoint unions of cycles and trees decompositions, and complete bipartite graphs decompositions of C 2 n , n. In the end, a recursive construction of an edge decomposition, based on orthogonal edge decompositions, is proposed. This helps in using the mutually orthogonal decompositions of the circulant graphs C 2 n , n in several applications, such as the design of experiments and binary codes generation. [ABSTRACT FROM AUTHOR]

In recent years, exploration of local characteristics have been an effective feature extraction technique for managing multimedia repository for image retrieval. These class of approaches accelerate the image retrieval. However, with the increase of online intrusion, it is also essential to provide confidentiality for the private online data with effective functionality and significant retrieval accuracy. In this paper, we have solved the protuberant bottleneck problem of privacy-preserving in CBIR using random projection technique for feature encryption with effective retrieval. For this, we formulated highly discriminative interest points based features that are rotation and translation invariant and are constructed using k -means clustering and silhouette concept. Moreover, we have devised locally likely arrangement hashing technique that can incorporate fast, accurate, and secure matching over encrypted features. Based on the experiment, it substantially outperforms the recent state-of-the-art techniques in terms of retrieval accuracy and time overhead on various standard benchmarks, namely, Corel, Olivia, ALOI, and MPEG-7. The proposed method on average provided retrieval accuracy of 83.10%, 81.30%, 81.62%, 73.01% for Corel, Olivia, ALOI and MPEG-7 plaintexted feature, respectively while retrieval accuracy of 79.90% for Corel, 79.10% for Olivia, 79.97% for ALOI, and 67.34% for MPEG-7 using the encrypted feature. [ABSTRACT FROM AUTHOR]

This paper is concerned with the stability and stabilization problems for T-S fuzzy systems with two additive time-varying delays. Firstly, a novel Lyapounov-Krasovskii functional (LKF) is constructed by delay-product-type functional method together with the state vector augmentation. In order to handle time-delay square terms introduced into the derivative of LKF, an extended binary quadratic function negative-determination lemma is proposed. A less conservative delay-dependent stability condition is developed since not only some new bounding technologies are employed to deal with integral terms, but also the proposed lemma is employed to dispose nonlinear time-delay terms in derivative of constructed function. Then, the corresponding controller design method for closed-loop delayed fuzzy system is derived based on parallel distributed compensation scheme. Finally, four numerical examples are given to illustrate the superiority and effectiveness of the proposed criteria. [ABSTRACT FROM AUTHOR]

Let G = (V , E) be a simple graph with vertex set as V and edge set as E. Within the framework of graph-based binary coding, a graph G is a threshold graph if and only if it can be generated by a binary code of the type 0 s 1 1 t 1 ... 0 s k 1 t k , where s i and t i are positive integers with 1 ≤ i ≤ k. This type of binary code is called a binary generating code of G. In this paper, we address a problem originally posed by Harary and Schwenk in [10] titled "Which graphs have integral spectra?" in which the main focus of our investigations lies in the Seidel Laplacian spectrum of G generated by 0 s 1 1 t 1 ... 0 s k 1 t k . We establish that all eigenvalues of G are integers and multiplicities of eigenvalues are equal to powers of bits 0 and 1 (sizes of strings of 0's and 1's) involved in a binary generating code of G. We exhibit a necessary and sufficient condition in terms of eigenvalues of the matrix associated with a graph-based G binary code to be Seidel Laplacian integral. Furthermore, for any prime p , we explore the Seidel Laplacian spectrum of zero-divisor graphs associated with the ring Z p m (where m is a positive integer) and the polynomial ring Z p [ x ] / (x p). [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel surface reconstruction method for unoriented points by establishing and solving a nonlinear equation system. By treating normals as unknown parameters and imposing the conditions that the implicit field is constant and its gradients parallel to the normals on the input point cloud, we establish a nonlinear equation system involving the oriented normals. To simplify the system, we transform it into a 0-1 integer programming problem solely focusing on orientation by incorporating inconsistent oriented normal information through PCA. We solve the simplified problem using flipping-based iterative algorithms and propose two novel criteria for flipping based on theoretical analysis. Extensive experiments on renowned datasets demonstrate that our flipping-based method with wavelet surface reconstruction achieves state-of-the-art results in orientation and reconstruction. Furthermore, it exhibits linear computational and storage complexity by leveraging the orthogonality and compact support properties of wavelet bases. The source code is available at https://github.com/mayueji/FISR_code. • We propose a novel surface reconstruction method by establishing and solving nonlinear equation systems numerically. • To tackle the nonlinear equation system, we innovatively propose the gradient-based criterion and value-based criterion. • Our method achieves state-of-the-art performance in orientation and reconstruction. Its linear complexity overcomes computational and storage bottlenecks. [ABSTRACT FROM AUTHOR]

Cross-modal hashing has attracted a lot of attention and achieved remarkable success in large-scale cross-media similarity retrieval applications because of its superior computational efficiency and low storage overhead. However, constructing similarity relationship among samples in cross-modal unsupervised hashing is challenging because of the lack of manual annotation. Most existing unsupervised methods directly use the representations extracted from the backbone of their respective modality to construct instance similarity matrices, leading to inaccurate similarity matrices and resulting in suboptimal hash codes. To address this issue, a novel unsupervised hashing model, named Structure-aware Contrastive Hashing for Unsupervised Cross-modal Retrieval (SACH), is proposed in this paper. Specifically, we concurrently employ both high-dimensional representations and discriminative representations learned by the network to construct a more informative semantic correlative matrix across modalities. Moreover, we design a multimodal structure-aware alignment network to minimize heterogeneous gap in the high-order semantic space of each modality, effectively reducing disparities within heterogeneous data sources and enhancing the consistency of semantic information across modalities. Extensive experimental results on two widely utilized datasets demonstrate the superiority of our proposed SACH method in cross-modal retrieval tasks over existing state-of-the-art methods. • We propose an informative multimodal correlation matrix construction approach. • We propose a multimodal structure-aware alignment network to bridge heterogeneous gaps. • Extensive experiments show SACH's superiority in cross-modal retrieval. [ABSTRACT FROM AUTHOR]

Session-based recommendations (SBR) aim to predict the user's next choice of items based on historical data. It is hard to access the interaction information between users and we can only analyze the user's behavioral preferences based on the current session characteristics, which makes the recommendation task in this field quite challenging. Recently, considerable research has grown up around the theme of SBR. Previous works apply attention mechanisms and Graph Neural Networks (GNN) to achieve remarkable results. However, these methods ignore two main points: one is losing sight of the specific position of items in the session; the other is to drive global preference with local preference without considering the offset of the target preference among items in the session. This paper proposes a Global Target Preference Attention Network (GTPAN) Model with position information for the session-based recommendation. We introduce a position-aware embedding module to eliminate the effect of position missing. Considering that each item in the session is potentially rich in latent information of target preference, we use a target preference attention layer to learn the target preference vector of the session. Extensive experiments on three real datasets show that the proposed GTPAN model outperforms state-of-the-art session-based recommendation methods, especially on datasets with long sessions. [ABSTRACT FROM AUTHOR]

Cross-modal hashing (CMH) has gained considerable attention due to its low storage and fast query speed. Most existing CMH research pursues the binary codes of each modality by preserving a similarity matrix which is computationally expensive. In this paper, we propose a Gaussian similarity preserving method for cross-modal hashing. By using the semantic transformation, our model can avoid computing the similarity matrix explicitly. We further employ the sequential learning approach to reduce the quantization error. Experimental results on three benchmark datasets clearly show that our proposed method can outperform the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Searching for the nearest neighbor is a fundamental problem in the computer vision field, and deep hashing has become one of the most representative and widely used methods, which learns to generate compact binary codes for visual data. In this paper, we first delve into the representation learning of deep hashing and surprisingly find that deep hashing could be a double-edged sword, i.e. , deep hashing can accelerate the query speed and decrease the storage cost in the nearest neighbor search progress, but it greatly sacrifices the discriminability of deep representations especially with extremely short target code lengths. To solve this problem, we propose a two-step deep hashing learning framework. The first step focuses on learning deep discriminative representations with metric learning. Subsequently, the learning framework concentrates on simultaneously learning compact binary codes and preserving representations learned in the former step from being sacrificed. Extensive experiments on two general image datasets and four challenging image datasets validate the effectiveness of our proposed learning framework. Moreover, the side effect of deep hashing is successfully mitigated with our learning framework. [ABSTRACT FROM AUTHOR]

The improvement of photovoltaic (PV) power prediction precision plays a crucial role in the new energy consumption. This paper proposes a composite prediction framework (DC (DWT-DAE)-CNN) consisting of dual clustering and convolutional neural network to achieve day-ahead prediction of PV power. To avoid the temporal uncertainty of PV power and the high-dimensional complexity of numerical weather prediction, the raw data are processed by Discrete Wavelet Transform (DWT) and Deep Autoencoder respectively (DAE) to reduce the data redundancy. Secondly, a dual clustering pattern based on dynamic time warping distance clustering and Fuzzy C-Mean (FCM) clustering is proposed to progressively realize the dynamic characteristics of the power curve and numerical clustering of the weather information data. Finally, the data from PV plants in northeast China are used for validation. The results show that the annual average day-ahead prediction AR of the DC (DWT-DAE)-CNN model can reach 90.17%, which is better than other competing models. In addition, the dual clustering pattern performs better than other traditional clustering patterns with the same predictor. Using this method to predict the PV output power can provide better theoretical guidance for the stable and safe operation of grid-connected PV. • A dual clustering model based on numerical variation and curve morphology variation is proposed. • The power data and NWP data were processed separately using Discrete Wavelet Transform and Deep Autoencoder. • Building multiple convolutional neural network predictors for PV power day-ahead prediction. • The proposed model was shown to outperform the comparison model under different seasons. [ABSTRACT FROM AUTHOR]

Highlights • A new algorithm of links labelling along with the binary code, is used for the isomorphism detection of kinematic chains. • Kinematic chains with simple and multiple joints, and also the Epicyclic gear chains have been tested very effectively. • Decoding of the binary codes for various kinematic chains is presented in a unique way. Abstract Isomorphism of kinematic chains (KCs) has always been a critical issue for the researchers dealing with structural synthesis. Consequently, many researchers of repute presented various methods during the last eight decades for the KCs with either simple and/or multiple joints. Binary code is one of such various methods, but the major problem lies in the algorithm of links labelling, which becomes cumbersome, in particular, for large KCs. The paper presents a simple algorithm of links labelling used to find out a binary sequence which, in turn, provides a maximum binary code (chain invariant). The algorithm is tested for six, seven, eight, nine, ten, eleven, twelve and fifteen links with simple joints, seven and eight links KCs with multiple joints and finally, the Epicyclic gear trains (EGTs) with four, five and six links for its efficiency and reliability. The results are in full agreement with the references taken for the purpose. The paper discusses, in a unique way, the decoding of the binary codes of different KCs also. [ABSTRACT FROM AUTHOR]

Graphical abstract Highlights • A method is proposed to characterize a computer program's runtime resource usage from the analysis of its binary executable file. • The approach produces a phylogeny (hierarchical clustering) of programs based on syntactic similarities found in the executable code. • Rationales are introduced to explain that these similarities in the binary file correlate to corresponding similarities in runtime behavior. • The placement of a program in the binary-code phylogeny bears resemblance to the relative similarity of its runtime behavior with respect to the other programs. • Experimental results show numerically significant evidences that the soft computing method is capable of characterizing runtime profile from binary-code similarities. Abstract This paper introduces a methodology for characterizing the runtime resource demands of a computer program from the analysis of its binary executable file. Categorization of applications according to the kind of resources required during execution – such as CPU and memory usage – is a sough-after piece of knowledge for the aims of computer system design and management. Conventional techniques available for this purpose include white-box static source code analysis and profile matching based on historical execution data. The former tends to be challenging in face of complex software architectures and requires access to the source code; the latter is dependent on the availability of reliable past data and on the selection of features yielding effective correlations with resource usage. The alternative data mining approach proposed in this paper avoids those difficulties by manipulating binary executable files. The method combines techniques from information theory, complex networks and phylogenetics to produce a hierarchical clustering of a set of executable files, which can be used to infer potential similarities in terms of runtime resource usage. The paper introduces the method's rationales and presents results of its application to characterize CPU and IO usages of benchmark applications executed on a standard PC platform. Essays carried out over a set of 80 programs from varying sources yielded numerically significant evidences that the prediction of resource usage similarity obtained by the approach is consistent with experimentally measured runtime profile. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a more robust supervised hashing framework based on the Cauchy loss function and Supervised Discrete Hashing (SDH) called Robust Supervised Discrete Hashing (RSDH), which can learn a robust subspace consisted of binary codes. The Cauchy loss is used to measure the error between the label matrix and the product of the decomposed matrices. RSDH can not only reduce the outliers and noise of the hashing codes, but also achieve the more satisfactory retrieval effect. Image retrieval experiments demonstrate that RSDH performs better than the other hashing methods. [ABSTRACT FROM AUTHOR]

• A deep neural network architecture is proposed to learn binary hash codes from physiological time series. • High utility, similarity preserving and temporal relationship are jointly learned with multiple designed objectives. • Experiments on ECG and EEG datasets show the effectiveness of the proposed method. In this paper, we aim to transform numerical physiological time series into binary hash codes, that can be further used for indexing large-scale dataset, or accelerating downstream tasks such as instance-based classification. We propose HITS to learn binary H ash codes from phys I ological T ime S eries. HITS first builds a very deep one-dimensional convolutional neural network to learn lower-dimensional representations from raw physiological time series. Then, HITS jointly learns high utility, similarity preserving, and temporal related compact binary codes by corresponding objectives with imposed. Finally, given a new physiological time series, HITS can encode it to a binary hash code. Experiments are performed on two real-world Electrocardiogram and Electroencephalogram datasets. The accuracy of a k-nearest classifier is used to evaluate the quality of codes. HITS outperforms the second-best baseline 7.42% on average of k = { 1 , 2 , 4 , 8 , 16 , 32 } with code length c = 48 , while reducing 45.51% searching time than the same length numerical vectors on average of c = { 16 , 24 , 32 , 48 , 64 }. HITS consistently achieve higher classification accuracy than compared methods using k-nearest classifier varying different k and code length. Thus, HITS learns better binary hash codes than compared methods. [ABSTRACT FROM AUTHOR]

In this paper we consider the problem of learning nearest-prototype classifiers in any finite distance space; that is, in any finite set equipped with a distance function. An important advantage of a distance space over a metric space is that the triangle inequality need not be satisfied, which makes our results potentially very useful in practice. We consider a family of binary classifiers for learning nearest-prototype classification on distance spaces, building on the concept of large-width learning which we introduced and studied in earlier works. Nearest-prototype is a more general version of the ubiquitous nearest-neighbor classifier: a prototype may or may not be a sample point. One advantage in the approach taken in this paper is that the error bounds depend on a ‘width’ parameter, which can be sample-dependent and thereby yield a tighter bound. [ABSTRACT FROM AUTHOR]

The paper presents the new variant of genetic algorithm using the binary codes through matrix for mobile robot navigation (MRN) in static and dynamic environment. The path planning strategy is established using the trace theory as the optimum controller, Sylvester Law of Inertia (SLI) and matrix simulation. The Matrix-Binary Codes based Genetic Algorithm (MGA) transforms the environment from chaos to array. Importantly, the paper proves the SLI by the real and experimental results for the statement “any robotics randomized environment transforms into the array.” Hence the model is presented as pre-optimized robotics by SLI and post-optimized robotics by trace. The simulation result is presented by using MATLAB software and the result obtained by proposed controller is optimal with respect to path and time when compared to other intelligent navigational controller. [ABSTRACT FROM AUTHOR]

This paper constructs a class of lattices whose discrete analogues are variable-length non-linear codes. The well-known discrete analogue of lattices and linear codes inspires our approach. We next design a variable length binary non-linear code called automorphism orbit code from a finite abelian p -group of rank greater than 1, where p is a prime. For each finite abelian p -group, codewords of the automorphism orbit code are variable-length codewords called automorphism orbit codewords. The homomorphisms between groups determine homomorphism codes , whereas automorphism orbit codes are specified by partitions of a number, orbits of group action, homomorphisms and automorphisms of groups. For some groups G and H , we shall use elements of H o m (G , H) to create a cover relation for bit strings of codewords of an automorphism orbit code and formulate a lattice of variable length non-linear codes. [ABSTRACT FROM AUTHOR]

In two previous papers we constructed new families of completely regular codes by concatenation methods. Here we determine cases in which the new codes are completely transitive. For these cases we also find the automorphism groups of such codes. For the remaining cases, we show that the codes are not completely transitive assuming an upper bound on the order of the monomial automorphism groups, according to computational results. [ABSTRACT FROM AUTHOR]

In this paper, we propose intra- and inter-feature orthogonal fusion (IIOF) of local and global features obtained from MS-SincResNet or MS-SSincResNet (a variant of MS-SincResNet) for music emotion recognition (MER). Given a raw waveform of music signal, MS-SincResNet/MS-SSincResNet is first used to learn several 2D representations having different receptive fields and obtain embeddings with time-frequency information from different layers. Then, local and global features are extracted from these embeddings. IIOF consisting of intra-feature OF and inter-feature OF is further employed to integrate both local and global features to obtain a discriminative descriptor for MER. The intra-feature OF is used to enhance the diversity of the global feature, and the inter-feature OF is utilized to reduce redundancies and produce complementary information between local and global features. The experimental results have demonstrated that the representation discriminability can be enhanced by IIOF considering the feature orthogonality. Furthermore, extensive experimental results have shown that the proposed method outperforms other state-of-the-art methods in terms of regression and classification tasks on the well-known MER datasets, including the DEAM dataset and the PMEmo dataset. The codes are available at https://github.com/PeiChunChang/MS-SSincResNet_with_IIOF. • We propose IIOF approach to effectively integrating local and global features. • IIOF is combined with MS-SincResNet and MS-SSincResNet for music emotion recognition. • The proposed method outperforms other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Based on good algebraic structures and practicabilities, generalized quasi-cyclic (GQC) codes play important roles in coding theory. In this paper, we study some results on GQC codes over Z 4 including normalized generating sets, minimal generating sets and normalized generating sets of their dual codes. As an application, new Z 4 -linear codes and good binary nonlinear codes are constructed from GQC codes over Z 4. [ABSTRACT FROM AUTHOR]

Multivariate time series forecasting has typically been a relevant and interesting topic in many fields, including economics, electricity consumption, solar energy, and traffic management. In these domains, owing to the complex dependencies among multiple variables and the mixed dependencies in the time dimension, it is challenging to forecast a multivariate time series precisely. Furthermore, most of the forecasting methods fail to capture the mixed influence of the different time-length dependencies among multiple variables. In this paper, a new deep learning framework is proposed for dealing with this challenging problem, named as mixed dependence time-series network (MDTNet). In this framework, stacked dilated convolutions and recurrent units are applied to extract the complex patterns in the long- and short-term mixed dependencies among multiple variables. The experiments show that our proposed framework yields significant results, outperforming the state-of-the-art baseline methods on three of the four benchmark datasets in large horizons and achieving a competitive performance in short horizons on all the benchmark datasets. [ABSTRACT FROM AUTHOR]

In this paper, we demonstrate a terahertz (THz) binary encoder based on graphene metasurface. The unit cell of the device consists of two parallel metal bars and two split-ring resonators (SRRs) embedded with two graphene ribbons. For two SRRs in the unit cell, one is connected to an electrode on the right side, and the other is connected to the electrode on the left side of the device, respectively. When no voltage is applied, the device has two passbands whose central frequencies locating at 0.85 THz and 1.14 THz, respectively. Unlike many THz tunable filters which modulate the amplitude of different bands at the same time, this encoder can achieve separately modulation of each passband. By electrically adjusting the Fermi energy of graphene on each SRR individually, the maximum modulation depth at the two central frequencies can be up to 80% and 87%, respectively. Furthermore, the function of THz frequency range binary coding is realized, i.e., four different binary coders of 11, 10, 01 and 00 are obtained in the transmission. Our work paves a new way for the development of multifunctional integrated THz devices, which will be of great significance in THz switching, communication and one-chip integrated THz system. We demonstrate a terahertz (THz) binary encoder based on graphene metasurface. The unit cell of the device consists of two parallel metal bars and two split-ring resonators (SRRs) embedded with two graphene ribbons. For two SRRs in the unit cell, one is connected to an electrode on the right side biased by voltage of U 1 , and the other is connected to the left electrode biased by voltage of U 2 , respectively. When no voltage is applied, the device has two passbands whose central frequencies locating at 0.85 THz and 1.14 THz, respectively. This encoder can achieve separately modulation of each passband. By electrically adjusting the Fermi energy of graphene on each SRR individually, the maximum modulation depth at the two central frequencies can be up to 80% and 87%, respectively. Furthermore, the function of THz frequency range binary coding is realized, i.e., four different binary coders of 11, 10, 01 and 00 are obtained in the transmission. Our work paves a new way for the development of multifunctional integrated THz devices, which will be of great significance in THz switching, communication and one-chip integrated THz system. [Display omitted] [ABSTRACT FROM AUTHOR]

In this paper, a novel unsupervised C ross- M odal retrieval method via S ufficient S cene R epresentation (CMSSR) is proposed. Distinguished from the existing methods which mainly focus on simultaneously preserving the mutually-constrained intra- and inter-modal similarity relation, CMSSR considers data of different modalities as the descriptions of a scene from different views and accordingly integrates information of different modalities to learn a complete common representation containing sufficient information of the corresponding scene. To obtain such common representation, Gaussian Mixture Model (GMM) is firstly utilized to generate statistic representation of each uni-modal data, while the uni-modal spaces are accordingly abstracted as uni-modal statistical manifolds. In addition, the common space is assumed to be a high-dimensional statistical manifold with different uni-modal statistical manifolds as its sub-manifolds. In order to generate sufficient scene representation from uni-modal data, a representation completion strategy based on logistic regression is proposed to effectively complete the missing representation of another modality. Then, the similarity between different multi-modal data can be more accurately reflected by the distance metric in common statistical manifold. Based on the distance metric in common statistical manifold, Iterative Quantization is utilized to further generate binary code for fast cross-modal retrieval. Extensive experiments on three standard benchmark datasets fully demonstrate the superiority of CMSSR compared with several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

With the advent of the big data era, multimedia data is growing rapidly, and its data modalities is also becoming diversified. Therefore, the demand for the speed and accuracy of cross-modal information retrieval is increasing. Hashing-based cross-modal retrieval technology attracts widespread attention, it encodes multimedia data into a common binary hash space, thereby effectively measuring the correlation between samples from different modalities. In this paper, we propose a novel end-to-end deep cross-modal retrieval framework, namely Clustering-driven Deep Adversarial Hashing (CDAH), which has three main characteristics. Firstly, CDAH learns discriminative clusters recursively through a soft clustering model. It attempts to generate modal-invariant representations in a common space by obfuscating the modality classifier, which tries to distinguish different modalities according to the generated representations. Secondly, in order to minimize the modal gap between feature representations from different modalities with the same semantic label, and to maximize the distance between images and texts with different labels, CDAH constructs a fused-semantics matrix to integrate the original domain information from different modalities, serving as self-supervised information to refine the binary codes. Finally, CDAH skillfully uses a scaled tanh function to adaptively learn the binary codes, which will gradually converge to the original tricky binary coding problem. We conduct comprehensive experiments on four popular datasets, and the experimental results demonstrate the superiority of our model against the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Person re-identification (re-ID) has made substantial progress in recent years; however, it is still challenging to search for the target person in a short time. Re-ID with deep hashing is a shortcut for that but, limited by the expression of binary code, the performance of the hashing method is not satisfactory. Besides, to further speed up retrieval, researchers tend to reduce the number of feature bits, which will cause more performance degradation. In this paper, we design the attribute-based fast retrieval (AFR), which leverages the attribute prediction of the model trained in a binary classification manner tailor-made for hashing. The attribute information is also used to refine the global feature representation by an attribute-guided attention block (AAB). Then, to fully exploit deep feature to generate the hash codes, we propose a binary code learning method, named self-distilling smooth relaxation (SSR). In this method, a simple yet effective regularization is presented to distill the quantized knowledge in the model itself, thus mitigating the lack of semantic guidance in the traditional non-linear relaxations. We manually label attributes for each person in dataset CUHK03 and evaluate our method on four authoritative public benchmarks (Market-1501, Market-1501+500K, CUHK03, and DukeMTMC-reID). The experimental results indicate that with the SSR and AAB, we surpass all the state-of-the-art hashing methods. And compared with reducing the feature bits, the AFR strategy is more effective to save search time. [ABSTRACT FROM AUTHOR]

• A novel variant of softmax loss based on hard mining is proposed to FGIR. • The proposed loss can separate the closest subspecies of fine-grained image. • Extensive experiments on several classical benchmarks demenstrate its effectiveness. Although there is abundant of investigations on fine-grained image retrieval, it is still an extremely challenging task in the field of computer vision, due to the character of small diversity in inter-class but large diversity within intra-class. To handle this task, loss functions are critical to the performance of a deep convolutional neural network in extracting the discriminative feature of the fine-grained image for retrieval. Recent studies showed that the global structure loss functions help to extract more discriminative features. In this paper, we introduce a novel global structure loss function, named Hard Decorrelated Centralized Loss, for further improving the representation for fine-grained image retrieval. The proposed loss is available in extracting the discriminative feature for dividing the most similar categories. In our experiments, we employ the proposed loss to train the convolutional neural network, which shows state-of-the-art performances on six classical fine-grained image retrieval benchmarks, e.g. CUB-200-2011 and Stanford Cars. [ABSTRACT FROM AUTHOR]

Designers usually retrieve and review existing relevant product images to draw inspiration when designing a new proposal. Obtaining reasonable retrieval results of a given target is a challenging task due to the large-scale, low-correlation searching process in the product image field. In this paper, an end-to-end skip-connected network is introduced to improve the accuracy of retrieval by directly addressing the above problems. In more detail, skip-connections are employed to combine the multi-resolution feature maps produced by a pre-trained backbone network, which provides important improvements to address the presence of large scale variance problem. And the second-order information of the multi-resolution feature maps is obtained by using gram matrix operation, which allows the network to exploit more representative features and their correlations. Experimental results indicate that the proposed method achieves better retrieval performance when compared to current state-of-the-art techniques on there normal benchmark datasets as well as the product image data. [ABSTRACT FROM AUTHOR]

• A robust approach for biomedical image retrieval. • Feature vector based on Zenrike moment features, curvelet features and Gradient orientation. • Focuses on both texture and shape information with minimum redundant data. • Experiments are conducted on four benchmark biomedical image databases. Biomedical image retrieval is a crucial side of computer-aided diagnosis. It helps the radiologist and medical specialist to spot and perceive the specific disease. This paper proposed an efficient approach for retrieving similar biomedical images based on the Zernike moment features, curvelet features and histogram of oriented gradients (HOG) feature. The Zernike polynomials based moments set defines the Zernike moment which is a global descriptor and it is capable of extracting both texture and shape information with minimum redundant data. The curvelet transformation is used to compute the edge-based shape information in form of curvelet histogram for the curves with discontinuity and the HOG features calculate the happenings of gradient orientation in the local areas of an image. The experiments were conducted on four benchmark biomedical image databases: HRCT dataset, Emphysema CT database, OASIS MRI database and NEMA MRI database respectively. The performance of the proposed approach was compared with many existing methods and achieved a better retrieval rate on all the four databases. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel algorithm to address the Network Alignment problem. It is inspired from a previous message passing framework of Bayati et al. [2] and includes several modifications designed to significantly speed up the message updates as well as to enforce their convergence. Experiments show that our proposed model outperforms other state-of-the-art solvers. Finally, we propose an application of our method in order to address the Binary Diffing problem. We show that our solution provides better assignment than the reference differs in almost all submitted instances and outline the importance of leveraging the graphical structure of binary programs. [ABSTRACT FROM AUTHOR]

• A new hashing method(CHOP) based on orthogonal projection is proposed. • Orthogonal-constrained and hash codes are used to connect seen and unseen classes. • CHOP can improve the discriminative of hash codes, and avoid the hubness problem. • Extensive experiments and results indicate the effectiveness of the proposed CHOP. Cross-modal retrieval has recently attracted much attention because it helps users retrieve data across different modalities. However, with the explosive growth of data, a large number of new emerging concepts (unseen classes) that have not been appeared in the training data (seen classes) bring great challenges to the traditional cross-modal retrieval. Nevertheless, most existing approaches mainly focus on improving cross-modal retrieval performance of seen classes, which may fail in the unseen classes. To address the challenge of zero-shot cross-modal retrieval, we propose an orthogonal method in this paper, i.e., Cross-modal Hashing with Orthogonal Projection (CHOP). It projects cross-modal features and class attributes onto a Hamming space, where each projection of cross-modal features is orthogonal to the mismatched class attributes. By so doing, the model can learn a discriminative and binary representation of each modality. In addition, the class attributes build a bridge to transfer knowledge from seen classes to unseen classes. Furthermore, the orthogonal constraint on binary codes can help to mitigate the hubness problem. Extensive experiments on three benchmark datasets show that the proposed CHOP is effective in handling zero-shot cross-modal retrieval. [ABSTRACT FROM AUTHOR]

Searching relevant articles from medical resources is an important search task in clinical decision support system. The technical contents and long length of biomedical articles make this search task more complicated than many other search tasks. Previous research on biomedical information retrieval (IR) is typically based on keyword search. In this paper we propose a new approach. Using our approach, a user can use the full article as a query. This reduces the burden on the users and generates an effective automatic query from many more useful search features. In this novel search scenario, we explore in detail several important factors for developing a successful biomedical articles retrieval system, especially focusing on how to automatically convert an article into an effective search query. Specifically, we evaluate the performance of single features with different parameter configurations, as well as combinations of these features using the techniques of learning to rank and rank fusion. Experimental results on PubMed collection show that the introduction field is the most useful feature for transforming a query. Furthermore, our experiments showed that combining multiple features can significantly improve the effectiveness of a search system. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) has experienced phenomenal expansion over the past few years and has emerged as one of the most dynamic sectors of the international market. Android has become the driving force behind the rapid development of the IoT, and malware is one of the most severe concerns. Android is an open-source platform with a significant number of users. The identification of Android malware has become more critical in cybersecurity due to the meteoric rise of Android malware over the past few years and the severity of the damage it inflicts on smartphone users. Existing traditional Android malware detection methods based on machine learning have achieved encouraging performance. Still, the solution requires a massive workforce of feature engineering to build dynamic or static features and continuous learning through pre-extracted features to maintain high performance in identifying malware. Therefore, technologies for end-to-end malware detection without human interaction are necessary. In response to the rapid evolution of Android malware, a convolutional neural network that can acquire knowledge without requiring feature extraction is ideally suited. This paper offers a unique classification approach for malware based on a convolutional neural network, with feature extraction selected from the current pre-trained models DenseNet169, Xception, InceptionV3, ResNet50, and VGG16. The proposed methods have an advantage over existing detection methods due to their end-to-end learning process. Our suggested approaches convert Android APK files to binary codes and RGB images for usage as inputs to deep learning models. These models are trained and evaluated using the CICInvesAndMal2019 dataset, which consists of 333 benign and 428 malicious applications. Experiments demonstrate that the proposed approaches achieve a classification accuracy of 95.24%, 95.24%, and 95.83% for DenseNet169, InceptionV3, and VGG16, respectively, on a 761-sample dataset of malware, which is superior to other compared algorithms. Compared to previous methods, our suggested methods are more applicable to Android IoT devices since they do not require manual feature engineering and consume fewer resources. [ABSTRACT FROM AUTHOR]

In this paper, we always assume that p and n > 3 are two distinct odd primes, m ≥ 2 is a positive integer, and gcd ⁡ (p m , 2 n (2 2 n − 1)) ≠ 1. Set r = p 2 or r = p 3 , we determine upper bounds on the number of inequivalent extended binary irreducible Goppa codes Γ (L , g) of degree r and length 2 n + 1 , where L = F 2 n ∪ { ∞ } is the support set and each g (x) is an irreducible polynomial of degree r over F 2 n . [ABSTRACT FROM AUTHOR]

Hashing has been widely studied in support of efficient multimedia retrieval due to its high computation and storage efficiency. However, existing multimedia hashing models are designed only for specific multimedia retrieval tasks, e.g. , cross-modal retrieval and composite multi-modal retrieval. To simultaneously support multiple multimedia retrieval tasks, multiple different hashing models should be equipped in a multimedia retrieval system. This paper proposes a Structured Multi-Modal Hashing (SMMH) method, which can learn only a hash model for multiple multimedia retrieval tasks. Specifically, we generate structured hash codes by independently projecting the modality data into the Hamming space, where each part of hash codes preserves the specific characteristic of the specific modality data, and they are collaborated to represent the whole multi-modal data. To bridge the heterogeneous gap between multiple modalities, a fusion multi-modal space is constructed based on structured hash codes with label and pair-wise semantic supervision. Besides, we learn hash functions for composite multi-modal retrieval by projecting heterogeneous modalities into the collaborative multi-modal features. Finally, we develop a discrete hash optimization strategy to efficiently solve binary hash codes. Extensive experiments show that our model outperforms the strong baseline methods on multiple multimedia retrieval tasks. Source codes are available at https://github.com/ChaoqunZheng/SMMH. • The generated hash codes can simultaneously handle multiple multimedia retrieval. • There is currently no work devoted to structured hashing. • Our model sufficiently exploits the available modal features. • The hash codes are learned directly in an efficient and fast manner. • Experimental results show the superior performance of our proposed method. [ABSTRACT FROM AUTHOR]

This paper proposes a low-complexity neural network decoder based on the layered min-sum algorithm to decode cyclic codes. By generalizing the layered min-sum algorithm to its neural network counterpart, the number of network weights decreases while retaining a good error correction performance. The Bose–Chaudhuri–Hocquenghem (BCH) codes, quadratic residue (QR) codes, and punctured Reed–Muller (RM) codes are selected as three exemplary binary cyclic codes. Simulation results show that the proposed neural decoder achieves superior performance with less computational complexity compared with the state-of-the-art neural network decoder. Further, a neural decoder incorporating the modified random redundant decoding (mRRD) algorithm is investigated to approach the performance of maximum-likelihood decoding for some short codes. [ABSTRACT FROM AUTHOR]

In this paper, a novel approach which can map high-dimensional, real-valued data into low-dimensional, binary vectors is proposed to achieve fast approximate nearest neighbor (ANN) search. In our paper, the binary codes are required to preserve the relative similarity, which makes the Hamming distances of data pairs approximate their Euclidean distances in ANN search. Under such constraint, the distribution adaptive binary labels are obtained through a lookup-based mechanism. The perpendicular bisector planes located between two kinds of data whose binary labels are different on only one specific bit are considered as weak hash functions. As just two kinds of data are taken into consideration during generation of the weak hash functions, the final strong hash functions are formed by combining the weak ones through boosting scheme to map all kinds of data into binary codes effectively. Experimental results show that our algorithm can encode the out of samples efficiently, and the performances of our method are superior to many state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Hashing algorithm has been widely used for efficient approximate nearest neighbor (ANN) search. Learning optimal hashing functions has been given focus and it is still a challenge. This paper aims to effectively and efficiently generate relative similarity preserving binary codes. Most existing hashing methods try to preserve the locality similarity by preserving direct distance similarity, while ignoring the relative similarity which advantages in ANN search. In this paper, this issue is solved by proposing the relative error which emphasizes that the ordinal relations in Hamming space and Euclidean space should be consistent with each other. We learn hashing projection functions via two steps. The first step adopts the lookup-based mechanism to find the optimal binary codes of training data, which can preserve the relative similarity and simultaneously adapt to data distribution. The binary codes in the first step are considered as supervision information in the second step. The objective of the second step is to learn hashing projection functions which can efficiently regenerate the binary codes in the first step. Aim to be in accordance with the property of data distribution, the hyper internal tangent planes of two specified spheres are chosen as hashing projection functions. Assisted by these projection functions, the time complexity of encoding process is greatly reduced. Experimental results on four public data sets demonstrate that our method outperforms many other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Let C ⊆ { 1 , ... , k } n be such that for any k distinct elements of C there exists a coordinate where they all differ simultaneously. Fredman and Komlós studied upper and lower bounds on the largest cardinality of such a set C , in particular proving that as n → ∞ , | C | ≤ exp (n k ! ∕ k k − 1 + o (n)). Improvements over this result were first derived by different authors for k = 4. More recently, Guruswami and Riazanov showed that the coefficient k ! ∕ k k − 1 is certainly not tight for any k > 3 and provided explicit improvements for k = 5 , 6 , which are immediately extendable to k > 6 modulo a conjecture on the maxima of certain polynomials. In this paper, we first prove their conjecture, completing the derivation of their new bound for any k. Then, we develop a different method which gives further substantial improvements for k = 5 , 6. [ABSTRACT FROM AUTHOR]

With the ever-increasing growth of massive high-dimensional data, deep learning to hash technology has been widely used for approximate nearest neighbor search on large-scale datasets, due to its remarkable efficiency and retrieval performance. In this paper, we propose a novel supervised deep hashing method, named Multi-granularity Feature Learning Hashing (MFLH), to learn compact binary descriptors. Specifically, we design an end-to-end trainable network to jointly learn feature representations and hash codes, in which a global stream and a local stream are responsible for learning feature representations with different granularities, and a hashing stream is devoted to encoding multi-granularity features into binary codes. In the local stream, a Cyclic Shift Mechanism (CSM) strategy is developed to assist mining more discriminative local fine information. In the meantime, an approximate sign activation function, which can be used for continuous optimization, is introduced to reduce quantization error. Furthermore, an improved variant of the triplet loss is presented to enhance the representation of pair-wise similarity for hash codes. Extensive experiments demonstrate that our proposed method significantly outperforms state-of-the-art hashing methods on the benchmark datasets, thereby verifying the effectiveness of our approach. Source code is provided for reproducibility. [ABSTRACT FROM AUTHOR]

Human identification is an important task that can help protect information security. Building deep learning models for human identification from Electrocardiogram (ECG) data is one of the highly promising technique. It has several unique advantages such as liveness detection, insensitive, easy to collect, higher security and so on. However, existing classifier-based methods only support closed-set identification, while existing matching-based methods are limited to high computational complexity. Besides, almost all methods only consider one-shot identification, which might be affected by occasional noise. In this paper, we propose CardioID to solve the above problems. CardioID learns binary codes from continuous ECG data which can identify faster than existing methods. It also supports identifying new person without the need to reconstructed or re-train the model. Besides, it can theoretically guarantee the recognition accuracy by introducing statistical hypothesis testing for making an identification decision. Experiments on real world ECG data show that CardioID can achieve 9.84% higher identification accuracy while saving 30.90% of running time compared with each of the second best baselines. [ABSTRACT FROM AUTHOR]

• Proposed a deep asymmetric hashing via unequal-dimensional embeddings. • Proposed a well-designed alternative optimization to solve the discrete problem. • Evaluated the effectiveness of the proposed method via three famous datasets. In recent years, Hashing has become a popular technique used to support large-scale image retrieval, due to its significantly reduced storage, high search speed and capability of mapping high dimensional original features into compact similarity-preserving binary codes. Although effectiveness achieved, most existing hashing methods are still some limitations, including: (1) Many supervised hashing methods only transform the label information into pairwise similarities to guide the hash code learning process, which will lead to the loss of rich semantic information between image pairs. (2) Some pioneer hashing methods use a relaxation-based strategy to solve discrete problems, resulting in a large quantization error. (3) Some supervised hashing methods handle the hashing learning procedure based on an asymmetric learning manner, and although this partially solves the problems of low efficiency and accuracy of symmetric learning strategy, they are all based on the embeddings of equal dimension, which leads to the reduction in the models representation ability and an increase in potential noise. To overcome the above limitations, in this paper, we propose a novel yet simple but effective hashing method, named Scalable Deep Asymmetric Hashing (SDAH). Specifically, SDAH is an end-to-end deep hashing method based on a fast iterative optimization strategy, which utilizes two real-valued embeddings of unequal dimensions, i.e., real-valued embeddings of images and labels, to flexibly perform asymmetric similarity computation. It can circumvent the use of the large pairwise similarity matrix by introducing an intermediate label matrix term which results in a remarkable reduction in the memory space cost. By doing this, the learned hash codes are more semantically informative for image retrieval tasks. Experimental results on several benchmark datasets highlight the superiority of SDAH in comparison with many state-of-the-art hashing methods. [ABSTRACT FROM AUTHOR]