An object can be consisting of various attributes, such as illuminance, appearance, shape, orientation, etc. Separately extract these attributes has enormous value in visual effects modeling, attribute-specific retrieval and recognition. Essentially, these attributes can be fairly abstract and thus need labels to extract. However, sometimes the labels of these attributes may not be available with training

Salient object detection based on deep learning has become one of the research hotspots in computer vision. How to effectively extract useful information is a key issue for saliency detection. Most of the existing methods integrate features extracted from convolutional neural networks indiscriminately. However, the features of different layers have different characteristics, not all of them are useful

In this paper, the finite-time stability (FTS) problems for a class of fractional order memristor-based neural network (FOMNN) with time delays are investigated. Based on the method of steps, set-valued mapping, the theory of differential inclusion and fractional order Gronwall inequality, a new delay dependent criterion for the FTS of FOMNN with time delays and the fractional order 0<μ<1 is derived

Among various Sound Event Detection (SED) systems, Recurrent Neural Networks (RNN), such as long short-term memory unit and gated recurrent unit, is used to capture temporal dependencies, but it is confined in its length of temporal dependencies, resulting in a failure to model sound events with long duration. What’s more, RNN is incapable to process datasets in parallel, leading to low efficiency

Point-of-interests (POIs) recommendations aim at recommending locations to users on social platforms by analyzing their histories or combining other information. At present, the different granularity of factors (i.e. time, geography and sociability) are not thoroughly studied in existing works. To deal with this problem, we propose a two-stage coarse-to-fine POI recommendation algorithm based on tensor

An important part of art history can be discovered through the visual information in monument facades. However, the analysis of this visual information, i.e, morphology and architectural elements, requires high expert knowledge. An automatic system for identifying the architectural style or detecting the architectural elements of a monument based on one image will certainly help improving our knowledge

In this paper, we address cross-domain multi-dimensional emotion regression through adversarial learning. This is done via a proper conduction of both dimensional and domanial adversarial learning. On the one hand, we conduct adversarial learning between emotion dimensions via a dimensional discriminator to achieve dimension-specific features through the attention mechanism for better determining dimensional

Although deep learning has achieved remarkable successes over the past years, few reports have been published about applying deep neural networks to Wireless Sensor Networks (WSNs) for image targets recognition where data, energy, computation resources are limited. In this work, a Cost-Effective Domain Generalization (CEDG) algorithm has been proposed to train an efficient network with minimum labor

Deep recurrent neural networks (RNN), such as LSTM, have many advantages over forward networks for nonlinear system modeling. However, the most used training method, backward propagation through time (BPTT), is very slow. In this paper, by separating the LSTM cell into forward and recurrent models, we give a faster training method than BPTT. The deep LSTM is modified by combining the deep RNN with

In recent decades, unmanned surface vehicles (USVs) are attracting increasing attention due to their underlying capability in autonomously undertaking complex maritime tasks in constrained environments. However, the autonomy level of USVs is still limited, especially when being deployed to conduct multiple tasks simultaneously. This paper, therefore, aims to improve USVs autonomy level by investigating

The Internet of Vehicles (IoV) can obtain traffic information through a large number of data collected by sensors. However, the lack of data, abnormal data, and other low-quality problems have seriously restricted the development and application of the IoV. To solve the problem of missing data in a large-scale road network, the previous research achievements show that tensor decomposition method has

This study presents a novel deep learning architecture for multi-class classification and localization of abnormalities in medical imaging illustrated through experiments on mammograms. The proposed network combines two learning branches. One branch is for region classification with a newly added normal-region class. Second branch is region detection branch for ranking regions relative to one another

We propose a distributed and decentralized Generative Adversarial Networks (GANs) framework without the exchange of the training data. Each node contains local dataset, a discriminator and a generator, from which only the generator gradients are shared with other nodes. In this paper, we introduce a novel, distributed technique in which workers communicate directly with each other, having no central

Domain adaptation aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. Previous methods mostly match the distribution between two domains by global or class alignment. However, global alignment methods cannot achieve a fine-grained class-to-class overlap; class alignment methods supervised by pseudo-labels cannot guarantee their

Anti-terrorism research is an important academic topic in current societies. The crucial features of attacked incidents can be obtained effectively by identifying phase division of terrorism history. To handle time-series issues, complex networks theories are efficient and reliable analysis solutions. Therefore, we propose an original community detection method for complex time-series networks. Especially

Rotating speed fluctuation is a key problem that affects the fault diagnosis performance of mechanical equipment. Deep learning theory can use deep neural networks to realize automatic feature extraction and classification, but the existing methods always have defects in computational efficiency and diagnosis error on dealing with this problem. In this paper, combined with the advantages of deep learning

In the coming era of big data, many advances and attempts have been witnessed in deep learning based remaining useful life (RUL) prediction methods which can construct the mapping relation between the massive information and the RUL. Existing studies leverage advanced deep networks for RUL prediction mainly generating the point estimates for the RUL while the prognostic uncertainty quantification is

The problem of adaptive neural network (NN) control and the dynamic surface control (DSC) method for a series of nonlinear systems with uncertainty is discussed in this paper. Unknown smooth functions can be approximated by radial basis function-neural networks (RBF-NNs) with arbitrary accuracy in nonlinear systems. The DSC scheme is introduced for nonlinear systems with uncertainty to overcome the

Script identification is an essential step in the text extraction pipeline for multilingual application. This paper presents an effective approach to identify scripts in scene text images. Due to the complicated background, various text styles, character similarity of different languages, script identification has not been solved yet. Under the general classification framework of script identification

In recent years, image fusion has attracted more and more attention, and many excellent methods have emerged. However, only a few studies on joint image fusion and super-resolution have been carried out, and the performance of existing methods is far from that of simple image fusion. To tackle such problem, we propose a novel joint fusion and super-resolution framework based on discriminative dictionary

The risk of incurring a road traffic crash has increased year by year. Studies show that lack of attention during driving is one of the major causes of traffic accidents. In this work, in order to detect driver distraction, e.g., phone conversation, eating, texting, we introduce a deep unsupervised multi-modal fusion network, termed UMMFN. It is an end-to-end model composing of three main modules:

The paper considers the stability of coupled impulsive neural networks with time-varying delays and saturating actuators in finite time. Based on a delayed state feedback controller, the stability of coupled impulsive neural networks with time-varying delays and saturating actuators can be achieved in finite time. Combined with Lyapunov-based finite-time stability theory, some sufficient conditions

Object detection in images collected by Unmanned Aerial Vehicles (UAVs) constitutes a challenging task in computer vision, due to difficulties of learning a well-trained object detection model for handling instances in UAV images with arbitrary orientations, variation in different scales, irregular shapes, etc. In order to facilitate object detection research and extend its applications in natural

Linguistic knowledge is useful for various NLP tasks, but the difficulty lies in the representation and application. We consider that linguistic knowledge is implied in a large-scale corpus, while classification knowledge, the knowledge related to the definitions of entity and relation types, is implied in the labeled training data. Therefore, a corpus subgraph is proposed to mine more linguistic knowledge

Lifelong learning is still a great challenge for cognitive robots since the continuous streaming data they encounter is usually enormous and no-stationary. Traditional cognitive methods suffer from large storage and computation consumption in this situation. Therefore, we propose a self-organizing and reflecting cognitive network (SORCN) to realize robotic lifelong cognitive development through incremental

This paper aims to investigate the fixed-time synchronization analysis for discontinuous fuzzy inertial neural networks in the presence of parameter uncertainties. By using a new variable transformation and differential inclusions theory, we first establish two kinds of drive-response differential inclusion systems. By designing some novel discontinuous control inputs and using Lyapunov-Krasovskii

In this paper, we propose a triple intersecting U-Nets (TIU-Nets) for brain glioma segmentation. First, the proposed TIU-Nets is composed of binary-class segmentation U-Net (BU-Net) and multi-class segmentation U-Net (MU-Net), in which MU-Net reuses multi-resolution features from BU-Net. Second, we introduce a segmentation soft-mask predicted by BU-Net, that is, candidate glioma region is generated

This paper further investigated the synchronization problem of the chaotic neural networks by utilizing the sampled-data control with actuator saturation. Firstly, an augmented two-side-looped Lyapunov functional including both the states of the error system and their derivative is constructed. Then the Wirtinger-based integral inequality in combination with the improved reciprocally convex matrix

This paper tackles the task of biomedical event detection, which includes identifying and categorizing biomedical event triggers. We find that the current biomedical event detection models driven by dependency fail to benefit more distinct improvement from the existing manual dependency embeddings. Here an interpretable hypothesis for the problem above is, that the model using manual dependency embeddings

Morphological networks constructed with structural magnetic resonance imaging (sMRI) images have been widely investigated by exploring interregional alterations of different brain regions of interest (ROI) in the spatial domain for Alzheimer’s disease (AD) classification. However, few attentions are attracted to construct a subband-based individual network with the sMRI image in the frequency domain

It is challenging to relocate the embedded positions of the watermark when 3D models are subjected to rotation attacks, because the vertex data of 3D models has no implicit order. This paper proposes a zero-watermarking scheme for 3D models, using the Beamlet transform method. First, the area of the 1-ring neighbourhood of each vertex is calculated. Then, the 1-ring neighbourhoods of the vertices with

This paper mainly studies the periodicity and exponential stability for a class of inertial neural networks (INNs) with time-varying delays. Without utilizing standard reduced-order transformation, by using the continuation theorem and Cauchy–Schwarz inequality, delay-dependent criteria shown by some algebraic inequalities are derived to ensure the existence of periodic solutions. Furthermore, by means

Knowledge Graph (KG) is identified as a major area in artificial intelligence, which is used for many real-world applications. The task of knowledge graph reasoning has been widely used and proven to be effective, which aims to find these reasonable paths for various relations to solve the issue of incompleteness in KGs. However, many previous works on KG reasoning, such as path-based or reinforcement

In this paper, a modified collaborative filtering (MCF) algorithm with improved performance is developed for recommendation systems with application in predicting baseline data of Friedreich’s Ataxia (FRDA) patients. The proposed MCF algorithm combines the individual merits of both the user-based collaborative filtering (UBCF) method and the item-based collaborative filtering (IBCF) method, where both

In this paper, we investigate the distributed control problem for multi-agent systems (MASs) subject to multiplicative and additive noises over switching networks, where both cooperative and antagonistic interactions coexist. The communication topology is governed by a continuous-time Markovian chain. A stochastic approximation technique is utilized to handle stochastic bipartite consensus with communication

This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The experiments include tests of focusing neuron networks of one or two hidden layers on synthetic and well-known image recognition data sets. The results demonstrated that the focusing neurons can move their receptive fields towards more informative inputs. In the simple two-hidden

Single Image Super-Resolution (SISR) is a fundamental and important low-level computer vision (CV) task, yet its performance on real-world applications is not always satisfactory. Different from the previous SISR research, we focus on a specific but realistic SR issue: How can we obtain satisfied SR results from compressed JPG (C-JPG) images, which is a ubiquitous image format to greatly release storage

Removing rain streaks from single image is mathematically ill-defined and the known strategies tend to over-smooth the background and remove image details. To tackle this problem, this paper proposes a novel two-stage system. Firstly, in view of the frequency and direction of rain streaks, Gabor filter is first used to suppress rain streaks. Based on the bases extracted from natural images, several

The stability and synchronization problems are addressed in this study for the memristor-based fractional-order fuzzy cellular neural networks with multiple delays. By using the Laplace transform method, fractional-order calculus approach and the method of complex function, three exponential stability criteria are derived. Compared with the existing results of the above system, the novel exponentially

By applying Zhang neural dynamics method, this study proposed, analyzed, and investigated a continuous-time model for solving the time-varying Schur decomposition (SD) problem. The proposed model is an explicit dynamics model that utilizes the time derivative information. The theoretical analysis of the proposed model is presented to verify its convergence and efficiency in solving the time-varying

The identification of disease-associated miRNAs can help people better understand the pathogenesis of diseases from a genetic perspective. Therefore, the prediction of miRNA-disease associations has received increasing attention. In this paper, we propose a new computational method NCFM (Neural network-based Collaborative Filtering Method) to predict miRNA-disease associations based on deep neural

Dropout is a very effective method in preventing overfitting and has become the go-to regularizer for multi-layer neural networks in recent years. Hierarchical mixture of experts is a hierarchically gated model that defines a soft decision tree where leaves correspond to experts and decision nodes correspond to gating models that softly choose between its children, and as such, the model defines a

This paper addresses the adaptive finite-time consensus tracking problem for high-order nonlinear multi-agent systems (MASs) with powers of positive odd rational numbers under prescribed performance. Since the virtual and actual control parts of the dynamics of each follower agent are power functions containing positive odd rational numbers, the method of adding a power integrator is used to overcome

Recently, a significant amount of research has been investigated on interpretation of deep neural networks (DNNs) which are normally processed as black box models. Among the methods that have been developed, local interpretation methods stand out which have the features of clear expression in interpretation and low computation complexity. Different from existing surveys which cover a broad range of

Adaptive gradient learning methods such as Adam, RMSProp, and AdaGrad play an essential role in training a very deep neural network. The learning rates of these optimizers are adaptively changed to accelerate the training process. And the convergence speed is much faster than SGD in many deep learning tasks such as classification and NLP tasks. However, recent works have pointed out that adaptive learning

Recommender systems are designed to help users find matching items from plenty of candidates in online platforms. In many online platforms, such as Yelp and Epinions, users’ behaviors are constantly recorded over time, and the users also can build connections with others and share their interests. Previous recommendation methods have either modeled the dynamic interests or the dynamic social influences

When authenticating illegal users, the existing account/password matching mechanism is only used to validate passwords. Therefore, it can not identify the web behavior of malicious users, such as identity fraud. In the case of fingerprint and face recognition mechanisms, which are prone to fraud, these mechanisms are still ineffective in preventing identity fraud. Recent years, behavioral analysis

This paper investigates the event-triggered dynamic feedback control for master–slave synchronization of neural networks with actuator saturation. Firstly, a novel event-triggered mechanism with an exponentially decaying term is proposed. It reduces the value of measure function, which corresponds to decrease the event-triggered frequency. Secondly, a dynamic feedback controller is designed to synchronize

This paper focuses on the cluster synchronization problem in the prescribed-time of a class of uncertain complex dynamical networks with switching signal which is characterized by average dwell-time constraint. Different from traditional complex dynamical networks, uncertainties, switching signals and nonlinear coupled properties have been introduced to the networks. By applying switched system theory

Despite drawing inspiration from biological systems which are inherently noisy and variable, artificial neural networks have been shown to require precise weights to carry out the task which they are trained to accomplish. This creates a challenge when adapting these artificial networks to specialized execution platforms which may encode weights in a manner which restricts their accuracy and/or precision

The quasi-containment control problems of heterogeneous multiplex networks are investigated in this paper. By applying the impulsive control to the followers in the networks, and proposing the jointly directed spanning tree, all the followers converge to a convex hull which is expended by multiple leaders. Based on the Lyapunov method and comparison principle of impulsive systems, sufficient criteria

It is now known that the spiking neuron is a basic unit of spiking neural networks (SNNs). Spiking neurons modulate the nervous cells via receiving external incentives, generation of action potential and firing spikes. The SNNs usually used for pattern recognition tasks or complex computation depending on the brain-like characteristic. Although the SNNs have no advantages comparing with the deep neural

Multi-label learning has attracted more and more researchers’ attention. It deals with the problem where each instance is associated with multiple labels simultaneously. Some methods improve the performance by constructing label-specific features. Specifically, the LIFTACE method constructs label-specific features by clustering ensemble techniques, which ignores the importance of label vectors and

This paper considers a new task of detecting heterogeneous parallel steganography (HPS) on streaming media. This task is to detect the existence of the confidential messages hidden in the frames of streaming media with multiple kinds of orthogonal steganographic methods. We target on detecting HPS in this work for low bit-rate Voice over Internet Protocol (VoIP) speech streams, which is a widely-used

As an important part of batch chemical industry scheduling problems, the multi-stage multi-product batch plant scheduling problem (MMSP) has been widely studied for decades. This problem is characterized by multiple stages with non-identical parallel units and operate based on customer orders. In this paper, we focus on the large scale MMSP and treat the minimization of make-span as the objective function

Feature selection has become an indispensable preprocessing step in an expert system. Improving the feature selection performance could guide such a system to make better decisions. Classifier ensembles are known to improve performance when compared to the use of a single classifier. In this study, we aim to perform a formal comparison of different classifier ensemble methods on the feature selection

In oral surgery, accurate segmentation of the teeth has critical significance for the orthodontic treatment and research. However, in the cone beam computed tomography (CBCT) images, the boundaries of the teeth are blurred and some tissues around the teeth have similar intensities to the teeth, which makes the tooth segmentation more difficult and challenging. In this paper, an accurate and automatic

Alzheimer’s disease (AD) is a progressive and irreversible neurodegenerative condition whose development is characterized by lateralized brain atrophies. In AD, the hippocampus is the first brain structure to present atrophy, which, although to a lesser extent, is also a precursor to the broader asymmetrical development of the human brain. Structural magnetic resonance (MR) imaging is capable of detecting