Search

Highlights • Development of a biological neural network model that allows long term simulation of brain activity. • Optimization of the model using multiple techniques that led to a speed-up of X200. • Presentation of alternative simulation frameworks for long term simulations., Simulations of neural networks can be used to study the direct effect of internal or external changes on brain dynamics. However, some changes are not immediate but occur on the timescale of weeks, months, or years. Examples include effects of strokes, surgical tissue removal, or traumatic brain injury but also gradual changes during brain development. Simulating network activity over a long time, even for a small number of nodes, is a computational challenge. Here, we model a coupled network of human brain regions with a modified Wilson-Cowan model representing dynamics for each region and with synaptic plasticity adjusting connection weights within and between regions. Using strategies ranging from different models for plasticity, vectorization and a different differential equation solver setup, we achieved one second runtime for one second biological time.

The chemi-thermo-mechanical pulping (CTMP) is an important process that produces fibers for paper-making, whose output fiber length distribution (FLD) directly determines the energy consumption and product quality of the subsequent papermaking production. Therefore, study on modeling and control of the output FLD is essential for improving pulp quality and saving energy in refining process. However, the output FLD of refining process has non-Gaussian stochastic distribution property, making it difficult to use conventional methods to establish the output FLD model effectively. Under the framework of stochastic distribution control theory, this paper presents a novel modeling approach for output probability density function (PDF) of fiber length in CTMP by combining with the improved wavelet neural network (WNN). In this context, the square root B-spline approximation principle is firstly adopted to extract the B-spline weights of fiber length PDF shape as the target outputs for the WNN based B-spline weights model. Secondly, a novel two-stage hybrid learning algorithm is proposed to establish the parameters system for the WNN based weighs model by defining a multi-objective evaluation index for modeling accuracy in advance. This learning algorithm integrates multi-objective NSGA II algorithm in the first stage for better initial solutions at a global scope, and gradient descent method is employed in the second stage for accurate solutions of WNN model parameters inside a local range. As a result, the final output PDF of fiber length is reconstructed by the estimated B-spline weights using the B-spline approximation principle again. Experiments using actual industrial data have demonstrated the superiority and practicability of the proposed method.

As a special type of neurodynamic methodology dedicated to finding zeros of equations, zeroing neurodynamics has shown a powerful ability in solving challenging online time-varying problems. Multi-linear systems, on the other hand, are a type of tensor equations with a wide range of applications. In this paper, a zeroing neurodynamics approach for solving multi-linear systems with M -tensors is proposed along with three specific accelerated finite-time convergent zeroing neurodynamics models, which breaks the limitations of a recently presented neural network approach termed continuous time neural network. Activation functions available in constructing zeroing neurodynamics models for solving multi-linear systems with M -tensors are also investigated in the rest of the paper. Theoretical analyses prove that the proposed zeroing neurodynamics approach is stable in the sense of Lyapunov stability theory and the proposed models converge to the theoretical solution in finite time. Finally, computer simulations are provided to substantiate the efficacy and superiority of the proposed zeroing neurodynamics models for solving multi-linear systems with M -tensors.

The complex and varied urban road conditions have always been a difficult and a pivotal component in the study of driverless technology especially at intersections. In China, it is necessary for driverless cars to understand the gestures of traffic police. To identify the traffic police gesture at the intersection, the key step is to detect the traffic police at the intersection. At present, the research on traffic police detection is still in its infancy, there exists common problems such as slow detection speed and other real time problems in this method, and there is not a standardized traffic police data set ether. For the real time problems, this paper introduces the attention mechanism, and proposes a new real-time detection method of traffic police based on attention mechanism. The method proposed in this paper has strong robustness and can quickly complete the target detection task. For the data set problem, this paper analyzes and discloses similar data sets published through research. In the meanwhile, this paper collects 24,530 video data on the actual road, and it extracts and saves 12,000 pictures containing traffic police at frame rate of 30FPS as traffic police detection training and validated data set.

In this paper, adaptive neural tracking control problem is considered for non-strict-feedback high-order nonlinear systems with quantized input signal. Compared with the logarithmic quantizer, the quantizer introduced in this paper can avoid chattering problem. The dynamic surface control (DSC) technique is introduced to solve the problem of ‘explosion of complexity’, which is appeared in the classic adaptive backstepping control of high-order nonlinear systems. The structural properties of radial basis function neural networks (RBF NNs) are used to simplify the design difficulty from the functions of whole state variables. According to the classic adaptive backstepping technique and neural network algorithm, an output tracking controller is designed, which can guarantee that all the signals of the closed-loop system are semiglobally uniformly bounded and the output of the system can track the reference signal. Finally, a numerical example is presented to verify the effectiveness of the proposed method.

Person re-identification is to recognize a pedestrian who has been observed at different places in monitoring system, which is done by computer automatically. Important practical significance can be found in this paper on improving the intelligence of monitoring system. There are two challenging problems needed to be solved for person re-identification, which is feature representation and matching. Designing a suitable feature representation method is both challenging and crucial. Ideally, the extracted features should be robust enough to cope with the various situations of the monitoring environment, such as posture difference, illumination changing, and shooting angle difference, etc. There are a lot of challenges for feature matching too, such as small sample size, inter-class confusion, and intra-class variation, etc. In order to meet these challenges, a new person re-identification scheme was put forward in this paper. The following three aspects would be used to describe it. First, an improved BOF feature extraction algorithm based on SURF was put forwarded, SURF algorithm extracts the preliminary feature descriptor and generates visual dictionary, so the influence factors such as illumination and scale invariants can be deal with. And then, covariance descriptor was adopted by the algorithm. It has high robustness, and matching accuracy can be improved too for the case of small sample. Finally, an effective classifier was designed by LIBSVM based on improved BOF algorithm, so the efficiency of the person re-identification algorithm can be improved. The proposed method was compared with the current mainstream algorithm through experiment, and it can be found through the experimental results that it is effective to solve the difficult problems for person re-identification.

Many methods achieve the visual object tracking task with deep learning technologies. As the deep features of different levels contain various semantic information and functions, this paper presents a multi-hierarchy feature aggregation approach to tackle the specific issues in the tracking task, which consists of two aspects. On one hand, this paper integrates the features captured by the offline and online classifiers at the score level, which constructs complementary roles of these classifiers to enhance the stability of classification. Besides, the proposed offline classifier is continuously optimized with different levels of features to reinforce classification constraints. On the other hand, we design a butterfly attention module to promote the capacity of multi-hierarchy feature aggregation in the regression network, which aims to fuse and strengthen the multi-scale features by attending to their spatial information. It can capture more spatial contexts by utilizing the self-attention mechanism during the fusion procedure, and preserve the hierarchy of the features during the strengthening process. Extensive experiments on four public datasets, i.e., VOT2018, OTB100, NFS and LaSOT datasets, demonstrate the effectiveness of the proposed methods.

Context and rationale Intrusion Detection, the ability to detect malware and other attacks, is a crucial aspect to ensure cybersecurity. So is the ability to identify this myriad of attacks. Objective Artificial Neural Networks (as well as other machine learning bio-inspired approaches) are an established and proven method of accurate classification. ANNs are extremely versatile – a wide range of setups can achieve significantly different classification results. The main objective and contribution of this paper is the evaluation of the way the hyperparameters can influence the final classification result. Method and results In this paper, a wide range of ANN setups is put to comparison. We have performed our experiments on two benchmark datasets, namely NSL-KDD and CICIDS2017. Conclusions The most effective arrangement achieves the multi-class classification accuracy of 99.909% on an established benchmark dataset.

Single-object tracking is regarded as a challenging task in computer vision, especially in complex spatio-temporal contexts. The changes in the environment and object deformation make it difficult to track. In the last 10 years, the application of correlation filters and deep learning enhances the performance of trackers to a large extent. This paper summarizes single-object tracking algorithms based on correlation filters and deep learning. Firstly, we explain the definition of single-object tracking and analyze the components of general object tracking algorithms. Secondly, the single-object tracking algorithms proposed in the past decade are summarized according to different categories. Finally, this paper summarizes the achievements and problems of existing algorithms by analyzing experimental results and discusses the development trends.

In the process of Human-robot skill transfer, we require the robot to reproduce the trajectory of teacher and expect that the robot can generalize the learned trajectory. For the trajectory after generalization, we expect that the robot arm can accurately track. However, because the model of the robot can not be accurately obtained, some researchers have proposed using a neural network to approximate the unknown term. The parameters of the traditional RBF neural network are usually selected through the empirical and trial-and-error method, which maybe biased and inefficient. In addition, due to the end-effector of the mechanical arm trajectory will be constantly changing according to the needs of the task, when the neural network of compact set cannot contain the whole input vector, the neural network cannot achieve the ideal approximation effect. In this paper, the broad neural network is used to approximate the unknown terms of the robot. This method can reuse the motion controller that has been learned and complete other motions in the robot operating space without relearning its weight parameters. In this paper, the effectiveness of the proposed method is proved by the ultrasound scanning task.

The problem of pursuing the data items of a large database whose distances to a query item are the least is known as Similarity Search (Nearest Neighbor Search) problem. There exist various algorithms to address this problem. Some of the well known algorithms are i) exact algorithms ii) approximation algorithms and iii) randomized algorithms. This paper has made study only on exact and approximation algorithms because randomized algorithm produces approximate results with some probability. Recently, there are several approximation algorithms are proposed by the researchers because this type of algorithms minimizes the problem of Curse of Dimensionality. This paper mainly has two major sections. In first section, various methods under exact and approximation algorithms are discussed with regard to storage, preprocessing and query time. In the second section, efficient algorithms for similarity search suitable for certain physiological characteristics based biometric systems are considered. Biometric system has five main steps viz acquisition of Image, pre-processing, extraction of features, matching and making final decision. In this paper, indexing algorithms for similarity search suitable for iris trait based on different features are discussed in detail. Since the nature of features are distinct and different in biometric traits, there does not exist a universal (one unique) solution which can apply to all traits of biometric systems. Various performance measures like Penetration Rate and Hit Rate are used to determine the correct recognition rate with top best match (rank-1 accuracy).

This paper proposes a hybrid architecture based on neural networks, fuzzy systems, and n-uninorms for solving pattern classification problems, termed as ENFS-Uni0 (short for evolving neuro-fuzzy system based on uni-nullneurons). The model can produce knowledge in an on-line (single-pass) and evolving learning context in a particular form of neuro-fuzzy rules representing the dependencies among input features through IF-THEN type relations. The rules antecedents are thereby realized through uni-nullneurons, which are constructed from n-uninorms, leading to the possibility to express both, AND- and OR-connections (and a mixture of these) among the single antecedent parts of a rule (and thus achieving an advanced interpretability aspect of the rules). The neurons’ evolution is done through an extended version of an autonomous data partition method (ADPA). On-line interpretation of the timely evolution of rules is addressed by (i) a concept for tracking the degree of changes of the rules over data stream samples, which may indicate experts/operators how much dynamics is in the process and may be used as a structural active learning component to request operator’s feedback in the case of significant changes and (ii) a concept for updating feature weights incrementally. These weights express the (possibly changing) impact degrees of features on the classification problem: features with low weights can be seen as unimportant and masked out when showing rules to an expert ( → rule length reduction). The rules’ consequents are represented by certainty vectors and are recursively updated by an indicator-based recursive weighted least squares (I-RWLS) approach (one RWLS estimator per class) where the weights are given through the neuron activation levels in order to gain stable local learning. The model proposed in this paper was successfully compared to related hybrid and evolving approaches in the literature for classifying binary and multi-class patterns. The results obtained by the proposed model show an outperformance of the related works in terms of higher accuracy trend lines over time, while offering a high degree of interpretability through coherent neuro-fuzzy rules to solve the classification problems.

Subtle facial expression recognition (SFER) aims to classify facial expressions with very low intensity into corresponding human emotions. Subtle facial expression can be regarded as a special kind of facial expression, whose facial muscle movements are more difficult to capture. In the last decade, various methods have been developed for common facial expression recognition (FER). However, most of them failed to automatically find the most discriminative parts of facial expression and the correlation of muscle movements when human makes facial expression, which makes them unsuitable for SFER. To better solve SFER problem, an attention mechanism based model focusing on salient local regions and their correlations is proposed in this paper. The proposed method: 1) utilizes multiple attention blocks to attend to distinct discriminative regions and extract corresponding local features automatically, 2) a correlation attention module is integrated in the model to extract global correlation feature over the salient regions, and finally 3) fuses the correlation feature and local features in an efficient way for the final facial expression classification. By this way, the useful but subtle local information can be utilized in more detail, and the correlation of different local regions is also extracted. Extensive experiment on the LSEMSW and CK+ datasets shows that the method proposed in this paper achieves superior results, which demonstrates its effectiveness.

The purpose of this paper is to give an overview of various well known medical image registration techniques with a special focus on registration between anatomical and functional medical images. Examples of anatomical medical images (AMI) are Computer Tomography (CT), Magnetic Resonance Images (MRI), X-ray radiographs and ultrasound etc. whereas Positron Emission Tomography (PET), Single Photon Emission Tomography (SPECT) and fMRI are examples of functional medical images (FMI). Irrespective of such types (AMI or FMI), every case can be considered as a medical imaging modality. All these modalities are widely used by clinicians to study the structure/functionality of human body parts for diagnosis and treatment. It is frequently required to combine PET/SPECT with CT/MRI to simultaneous study the metabolic and molecular information received through PET/SPECT with fine anatomical details observed by CT/MRI. This concurrent study will help in the diagnosis and localization of many diseases like cancer, blockage in coronary arteries and brain-related diseases like Parkinson, Alzheimer etc. Further, in many cases, clinicians are required to co-register one or more anatomical images with functional images, for example, ultrasound-guided biopsy fused with PET and MRI. This registration can be done either at the hardware level or at the software level. The introduction of integrated PET-CT machine increases the acceptability of hardware-based registration systems as compared to software-based methods among the medics. One possible reason for this is the lack of validation of results achieved through software-based registration methods. On the other hand, software-based registration methods also have many advantages over the hardware-based registration systems like lesser exposure to radiation and no need for new investment on hardware etc. In this paper, both the methods with their merits and demerits are discussed in detail.

Extreme-learning-machine based auto-encoder (ELM-AE) is regarded as a useful architecture with fast learning speed and general approximation ability, and stacked ELM is used to develop efficient and effective deep learning networks. However, considering features learned from conventional ELM-AEs have issues of weak nonlinear representation ability and random factors in feature projection, this paper proposes an improved ELM-AE architecture which utilize low-rank matrix factorization to learn optimal low-dimensional features. Two superiorities can be obtained compared to conventional ELM-AEs. One is the dimensionality of the hidden layer in ELM-AE could be set arbitrarily, e.g. a higher-dimension hidden layer could lower the random effect in feature learning and enhance features representation ability. The other is enhancing features nonlinear ability, since features are learned directly from the nonlinear outputs of hidden layer. Finally, comparison experiments on numerical and image datasets are implemented in this paper to verify the superior performance of the proposed ELM-AE in this paper.

Deep learning has made substantial progress in crowd density estimation, but in practical application, due to the interference factors such as uneven distribution of crowd and changes in illumination, the existing methods still have large errors in counting. To solve the above problems, a crowd density estimation method based on multichannel dense grouping network is proposed. To solve the problem that it is difficult to extract the multiscale information of the crowd due to the uneven distribution of the crowd, multichannel dense grouping module (McDGM) is designed. In the module, Improved grouping convolution block (IGCB) is dense connected with other layers to obtain different levels of crowd characteristics, so as to avoid the loss of multi-scale information. In addition, the parameters of IGCB are reduced by group convolution. Then, to overcome the change of illumination, a crowd image enhancement algorithm is designed, which makes the image clear by the average pixel value and adjusting the contrast. Finally, to enhance the sensitivity of the network to crowd counting, a new loss function is proposed, which adds counting loss to the previous pixel space loss to improve the accuracy of crowd counting. The algorithm in this paper has been tested on ShanghaiTech and UCF_CC_50 datasets. The test results show that the algorithm in this paper has better statistical accuracy.

From the perspective of large-scale system, a directed complex dynamic network (DCDN) may be considered as a coupling system of the node subsystem (NS) and the link subsystem (LS). In this paper, by using the outgoing link vector and incoming link vector for DCDN, the dynamics of LS is described by employing the vector differential equation instead of the matrix differential equation. Since the outgoing and incoming link vectors have the stronger geometric intuition, the results in this paper show that this kind model of links can not only reflect the direction of links but also find the dynamic tracking goal of links more easily when the state synchronization of NS emerges. Furthermore, by employing the simple mathematical conditions, the nonlinear controller of NS and the coupling term of LS are proposed to ensure achieving the asymptotical state synchronization for DCDN. Finally, the numerical simulations are given to demonstrate the validity of the results in this paper.

In this paper, a neural synchronization of the optimal structure-based group of neural networks is proposed. Asymmetric cryptography is widely used to generate a key amongst two parties and to exchange the key through an insecure channel. However, since the methods that used this strategy, like RSA, have been compromised, new methods for producing a key that can offer security must be discovered. A new group of cryptography known as neural cryptography was created to solve this issue. The primary aim of neural cryptography is to produce a secret key over an unreliable medium. The optimal neural network architecture for creating and defining a secret key between the two authorized individuals is examined in this article. Furthermore, studies into the coordination of a group of neural networks are uncommon. For the design of the public key exchange protocol, synchronization of a cluster of neural networks with Three Layer Tree Parity Machine (TLTPM) is proposed. To calculate the synchronization time, steps taken, and the number of times the attacking neural network could replicate the actions of the two accepted networks, more than 15 million simulations were run. Various parametric experiments have been conducted on the proposed methodology. Simulations of the approach show that it is correct, according to the results of the paper.

This paper tackles the event-triggering filtering problem for a class of nonlinear networked control systems subject to the prescribed disturbance attenuation level. To alleviate the data transmission burden of communication channels, an event-triggering mechanism is adopted, where the data can be transmitted only if certain condition is fulfilled. The T-S fuzzy model approach is utilized to approximate the nonlinear dynamics. It is the purpose of this paper to design a filter for the addressed nonlinear system ensuring that the filtering error system is asymptotically stable whereas the prespecified H ∞ criterion is guaranteed. By using Lyapunov approach in combination with matrix analysis method, the sufficient conditions are established for the existence of desired filtering parameters in terms of the solvability of certain linear matrix inequalities. Finally, a numerical simulation example is put forward to demonstrate the validity and effectiveness of the developed theoretical results.

This paper investigates the motion control of a Stewart parallel robot with uncertain load. The external disturbances caused by load can trigger dynamic coupling among six degree-of-freedoms and have a significant impact on control precision. In practice, the dynamic parameters of load is difficult to be precedent identified and the robot with load is a multi-input multi-output(MIMO) system in physical space, which makes the dynamic coupling problem difficult to solve effectively and the high-performance control is hard to achieve. In this paper, the dynamic effect of the load is first analyzed. Then a novel motion control method, modal space neural network compensation control, is designed with the aim of reducing the effect of the load disturbances. This controller implements the neural network to compensate for the load disturbances. In addition, the modal space control theory is introduced to realize the independent control of each control channel. The feasibility of the proposed controller is evaluated in numerical simulations. Results reveal that the proposed control method gives exceptional tracking performance and dynamic coupling suppression capability.

With the rapid development of deep learning technology and improvement in computing capability, deep learning has been widely used in the field of hyperspectral image (HSI) classification. In general, deep learning models often contain many trainable parameters and require a massive number of labeled samples to achieve optimal performance. However, in regard to HSI classification, a large number of labeled samples is generally difficult to acquire due to the difficulty and time-consuming nature of manual labeling. Therefore, many research works focus on building a deep learning model for HSI classification with few labeled samples. In this article, we concentrate on this topic and provide a systematic review of the relevant literature. Specifically, the contributions of this paper are twofold. First, the research progress of related methods is categorized according to the learning paradigm, including transfer learning, active learning and few-shot learning. Second, a number of experiments with various state-of-the-art approaches has been carried out, and the results are summarized to reveal the potential research directions. More importantly, it is notable that although there is a vast gap between deep learning models (that usually need sufficient labeled samples) and the HSI scenario with few labeled samples, the issues of small-sample sets can be well characterized by fusion of deep learning methods and related techniques, such as transfer learning and a lightweight model. For reproducibility, the source codes of the methods assessed in the paper can be found at https://github.com/ShuGuoJ/HSI-Classification.git.

This paper considers the leader-following consensus problem for delayed neural networks with multi-layer signed digraph topologies. Both structurally balanced and unbalanced topologies are considered. By using the structural balance theory and the pinning control strategy, some sufficient conditions are given to guarantee that the bipartite leader-following consensus can be reached in structurally balanced multi-layer signed neural networks, which depend on the node dynamics and the topology of the multi-layer signed network. In addition, a scheme is designed for selecting the pinning nodes and gains of each layer to achieve bipartite leader-following consensus. When the multi-layer signed network is structurally unbalanced, the asymptotic stability of the neural network is investigated by decomposing the structurally unbalanced network into a structurally balanced subgraph and some special edges. The conditions proposed in this paper are also suitable for addressing the consensus problem of traditional single layer signed neural networks. Numerical examples are given to illustrate the correctness and effectiveness of the proposed theorems and algorithms.

This paper considers the stochastic consensus problem of high-order linear discrete-time multiagent systems (MASs) with uncertain topologies and external disturbances. The randomly switching interaction signed topologies are governed by a time-homogenous Markov chain with incomplete knowledge of the transition probabilities. Based on Lyapunov function theory and adaptive control strategies, we employ a homogeneous parameter-dependent Lyapunov function to propose sufficient conditions under a set of linear matrix inequality (LMI) constraints. A free-weighting matrix method is introduced to give the proposed LMIs extra freedom to search feasible solutions. Furthermore, the adaptive controllers applied in this paper are independent of topologies and fully distributed; i.e., the system achieves robust consensus without continuously updating the controller and dealing with global data. Additionally, we extend the theoretical framework to analyze the disturbance rejection performance of MASs under the stochastic process. Two numerical examples are provided to show the effectiveness of the algorithms.

This paper presents a novel nonlinear adaptive sensor fusion method for integrated navigation systems with varying noise parameters. The innovation is utilizing deep neural networks to mine the noise-related patterns of specific sensors and combining it with conventional nonlinear filters. This hybrid approach improves the feasibility and robustness of adaptive filtering by achieving an effective estimation of the originally weakly observable noise parameters. The specific sensors are defined as α -type sensors whose errors are entirely generated by themselves. The mathematical model for analyzing α -type sensors output sequence and the deep neural network for mining the patterns of interest are established. All adaptive filtering systems using α -type sensors can benefit from this paper. Specifically, it is applied to inertial and satellite integrated navigation system. The numerical experiments indicate that the proposed filter achieves promising accuracy and robustness improvement as compared to conventional nonlinear filters. And the comparisons between different nonlinear approximation algorithms indicate that the first-order approximation is accurate enough for our application.

This paper presents the neural dynamical network to compute the generalized and restricted singular value decompositions (GSVD/RSVD) in the regularization methods for ill-posed problems. The neural network model is defined by ordinary differential equations (ODE) which can be solved by many state-of-the-art techniques. The main purpose of the paper is to develop two neural network models for finding approximations of the GSVD and the RSVD. The globally asymptotic stability analyses are provided and numerical experiments illustrate our theory and methods. For small scale problems, the estimation can be as accurate as O ( 10 - 15 ) . For ill-posed problems, the truncation regularization method implementing the GSVD/RSVD algorithms also produces accurate results.

Time-varying linear complementarity problem (TLCP) has received a great deal of attention due to its broad variety of scientific and engineering applications. Several efficient Zhang neural networks are introduced for solving TLCP in this paper. Theoretical analysis shows that the related error function of the model proposed in this paper eventually tends to zero. The state convergence time periods of those Zhang neural networks with three types of activation functions are proved to be finite and can be quantitatively estimated by using some given parameters. Further, it is shown that the proposed neural network is of noise-tolerance, which means the neural network is more appropriate for a wider application. Moreover, in order to implement neural network numerically, a related discrete-time version is also studied. Finally, numerical simulations confirm the analysis of the proposed models concretely.

This paper solves the fault-tolerant control (FTC) problem of uncertain nonlinear systems in nonstrict-feedback form. The controlled plants considered in this paper are more complicated than existing ones, which is composed of the unknown nonlinearities, unmeasured states, and sensor faults and unknown dead zone input nonlinearity. Fuzzy logic systems and a fault-estimation-based state observer are used for identifying the unknown nonlinearities and obtaining the unmeasured states, respectively. By designing the sensor faults compensation and the dead zone inverse compensation methods, an observer-based fault-tolerant compensation control scheme is developed under backstepping recursive design frame. And it is testified that the closed-loop signals are bounded, and the tracking performance is satisfied even when the controlled systems are not free of sensor faults and unknown dead zone input nonlinearity. An electromechanical system is used to test the effectiveness of the developed control strategy.

This paper proposes a solution to translating the visible images into infrared images, which is challenging in computer vision. Our solution belongs to unsupervised learning, which has recently become popular in image-to-image translation. However, existing methods do not produce satisfactory results because (1) most existing methods are mainly used in entertainment scenarios with single scenes and low complexity. The problem solved by this article is more diverse and more complicated. (2) The infrared response of objects depends not only on itself but also on the current environment, and existing methods cannot correlate long-range dependent objects. In this paper, We propose Global Spatial Attention (GSA), which enhances dependence between long-range objects and improves the synthesized image quality. Compared with other methods, GSA can save more space and time. Moreover, we introduce the idea of subspace learning into the neural network to make training more stable. Our method takes unpaired visible images and infrared images for training, which are easy to collect. Experimental results show that our method can generate high-quality infrared images from visible images and outperforms state-of-the-art methods.

Road landmark inventory is becoming an important data product for the maintenance of transport infrastructures. Several commercial sensors are available which include synchronized optical cameras that allowto build 360° panoramic images of the surroundings of the vehicle used for road inspection. This paper is devoted to the analysis of such panorama images,specifically the area that contains themost relevant information. Road lane landmark detection is posed as a two class classification problem that may be solved bymachine learningapproaches, such as Random Forest (RF) and ensembles of Extreme Learning Machines (V-ELM). Besides model parameter selection, a central problem is the construction of a labeled training and validation datasetto cope with the highly uncontrolled conditions of image capture. Besides, human labor cost makes image data labeling a very expensive process. This paper proposes an open ended Active Learning (AL) approach involving a human oraclein the loop who provides the data labeling and can trigger the AL process when detection quality is degraded by the change in imaging conditions. The paper reports encouraging results over a collection of sample images selected from an industrial road landmark inventory operation. As an additional contribution, this paper assesses the ability of AL to overcomesome of the issues raised by highly class imbalanced datasets.

Multi-view clustering has gained soar attention in the field of data mining in recent years. Most multi-view clustering methods are considered to be complete for each view. However, in many applications, some views may contain missing instances, resulting in the incomplete multi-view learning problem. Incomplete views cannot be directly dealt with traditional multi-view clustering methods. In this paper, we propose a One-step multi-view subspace clustering with incomplete views (OMVSC-IV) method based on low-rank matrix factorization to overcome this problem. Specifically, the proposed algorithm uses low-rank matrix factorization to learn a consensus representation matrix, and then combined with the objective function of non-negative embedding and spectral embedding subspace clustering proposed in this paper. The whole process is established into the same objective function for joint optimization and requires no post-processing (e.g., K-means), thus avoiding the defect of being sensitive to initial values. Furthermore, the accuracy, parameter, sensitivity and convergence of the algorithm are studied by experiments. Experimental results on nine data sets show that the proposed algorithm performs superior to some of the latest algorithms.

Depth estimation is a classic task in computer vision, which is of great significance for many applications such as augmented reality, target tracking and autonomous driving. Traditional monocular depth estimation methods are based on depth cues for depth prediction with strict requirements, e.g. shape-from-focus/ defocus methods require low depth of field on the scenes and images. Recently, a large body of deep learning methods have been proposed and has shown great promise in handling the traditional ill-posed problem. This paper aims to review the state-of-the-art development in deep learning-based monocular depth estimation. We give an overview of published papers between 2014 and 2020 in terms of training manners and task types. We firstly summarize the deep learning models for monocular depth estimation. Secondly, we categorize various deep learning-based methods in monocular depth estimation. Thirdly, we introduce the publicly available dataset and the evaluation metrics. And we also analysis the properties of these methods and compare their performance. Finally, we highlight the challenges in order to inform the future research directions.

Recently, due to its widespread applications in public safety, anomaly detection in crowd scenes has become a hot topic. Some deep-learning-based methods attain significant achievements in this field. Nevertheless, most of them suffer from over-fitting to some extent because of scarce data, which are usually abrupt and low-frequency in the real world. To remedy the above problem, this paper firstly develops a synthetic anomaly event generating system, which could simulate typical specific abnormal events. By utilizing this system, a large synthetic, diverse anomaly event dataset is built, which contains 2,149 video sequences. After getting the dataset, a 3D CNN is designed to detect the abnormal types at the video level. However, we find that there are obvious domain differences (also named as “domain gap/shifts”) between synthetic videos and real-world data, which results in performance degradation when applying the model to the real world. Thus, this paper further proposes a cyclic 3D GAN for domain adaption to reduce the domain gap, which translates the synthetic data to the photorealistic video sequences. Then the detection model is trained on the translated data and it can perform well in the real data. Experimental results illustrate that the proposed method outperforms these baselines for the domain adaptation anomaly detection.

This paper discusses the containment control (CC) problem of general linear multi-agent systems (MAS)s by means of two kinds of distributed event-triggered mechanisms. Two types of event-triggered control protocols, namely, the state feedback control law and the dynamic output feedback control protocol, are designed for each follower. Under the proposed control protocols and triggering mechanisms, the containment control problem can be solved by proving that the containment error converges to zero based on the assumption and algorithms. At last, we verify the rationality of the theoretical results. Through two numerical simulation, we can see that the trajectory of each follower converges to the convex hull formed by all leaders. In addition, in order to verify the advantages of the obtained results, we give a simulation example and compare the methods designed in this paper with the methods in other literature.

While meta learning approaches have achieved remarkable success, obtaining a stable and unbiased meta-learner remains a significant challenge, since the initial model of a meta-learner could be too biased towards existing tasks to adapt to new tasks. In order to avoid a biased meta-learner and improve its generalizability, this paper proposes a generic meta learning method that aims to learn an unbiased meta-learner towards a variety of tasks before its initial model is adapted to unseen tasks. Specifically, this paper presents a meta weight learning method for minimizing the inequality of performance across different training tasks. An end-to-end training approach is introduced for the proposed algorithm that allows for effectively learning weight and initializing the network model. Alternatively, a variety of measurement methods of weight is also designed to test the effectiveness of different weight learning methods on the improvement of model-agnostic meta-learning algorithm. The simulation results show that the proposed meta weight learning method not only outperforms state-of-the-art meta learning algorithms, but also is superior to other manually designed measurement methods of weight on discrete and continuous control problems.

Human intention prediction is of great significance in many applications, such as human-robot interaction, intelligent rehabilitation robots. This paper studies the problem of short-term next-active-object prediction in egocentric images. The short-term next-active-object refers to the object that a human is going to interact with in the short-term future, which is an embodiment of human intention. Most current methods usually use object-centered cues, such as the deviation of object appearance change and the unique shape of the egocentric object trajectory, to predict the next-active-object. In this paper, inspired by the fact that human intention is also revealed by human-centered cues, we propose a deep neural network model that integrates the cues from visual attention and hand positions to predict the next-active-object. Firstly, the probability maps of visual attention and hand positions are constructed, and then the probability distribution of next-active-object is generated. We experimentally compare our method with several baseline methods using two datasets and confirm its effectiveness. In addition, ablation experiments are conducted, and crucial points concerning the next-active-object are discussed.

Peer reviews form an essential part of scientific communications. Research papers and proposals are reviewed by several peers before they are finally accepted or rejected for publication and funding, respectively. With the steady increase in the number of research domains, scholarly venues (journal and/or conference), researchers, and papers, managing the peer review process is becoming a daunting task. Application of recommender systems to assist peer reviewing is, therefore, being explored and becoming an emerging research area. In this paper, we present a deep learning network based Meta-Review Generation considering peer review prediction of the scholarly article (MRGen). MRGen is able to provide solutions for: (i) Peer review prediction (Task 1) and (ii) Meta-review generation (Task 2). First, the system takes the peer reviews as input and produces a draft meta-review. Then it employs an integrated framework of convolution layer, long short-term memory (LSTM) model, Bi-LSTM model, and attention mechanism to predict the final decision (accept/reject) of the scholarly article. Based on the final decision, the proposed model MRGen incorporates Pointer Generator Network-based abstractive summarization to generate the final meta-review. The focus of our approach is to give a concise meta-review that maximizes information coverage, coherence, readability and also reduces redundancy. Extensive experiments conducted on the PeerRead dataset demonstrate good consistency between the recommended decisions and original decisions. We also compare the performance of MRGen with some of the existing state-ofthe- art multi-document summarization methods. The system also outperforms a few existing models based on accuracy, Rouge scores, readability, non-redundancy, and cohesion.

The problem of distributed fixed-time leader-following consensus tracking control for nonholonomic chained-form dynamic systems with nonlinear disturbances is considered in this paper. Compared with the existing works, this paper considers a class of more general nonholonomic multi-agent systems where both the leader and the followers have nonlinear uncertainties. For undirected graphs, a distributed observer for each follower is investigated such that both the leader state and input can be estimated by the followers in a fixed time. Based on the distributed observers, a consensus tracking controller is proposed to ensure that the tracking errors convergence to zero within a fixed time. Lyapunov analysis proves the stability of the closed-loop system. A simulation example of wheeled mobile robots is given to demonstrate the effectiveness of the proposed controllers.

This paper investigates the problem of neural network (NN) prescribed performance tracking control for a class of switched stochastic nonlinear pure-feedback systems which contain unknown nonlinear functions, unmeasured state variables, and unknown hysteresis input. It provides an adaptive NN controller which is not restricted to a particular type of hysteresis input. A general mathematical model is introduced to describe two kinds of hysteresis nonlinearities and to utilize in the control design producer. Other focus of this paper is on the performance constraint problem to avoid performance degradation and system damage in practical control systems. Prescribed performance control (PPC) and backstepping technique are thus synthesized to develop an adaptive NN output feedback tracking control scheme under deterministic switching signal. Regarding this concern, to cope with the cause of non-differentiable difficulties and complex deductions in traditional PPC, a new asymmetry error transformation is employed. Moreover, radial basis function NNs (RBFNNs) are applied to approximate the unknown nonlinear functions and to construct a NN nonlinear observer to estimate the immeasurable state variables. Based on Lyapunov stability theory, it is demonstrated that the proposed controller can guarantee that all signals in the closed-loop system are semiglobally uniformly ultimately bounded in probability and the tracking error converges to a small neighborhood of the origin with the prescribed performance bounds. Finally, two simulation examples are provided to confirm the advantages of the presented control design approach.

With the booming development of smart phones and location-based services, spatial keyword queries of semantic trajectories can take location information and multiple keywords as parameters and return semantic trajectories related to these parameters in space and text. With the development of the Location Based Social Network (LBSN) in recent years, social data can be used to improve query results. Generally, the semantic trajectory of having more supporters (users with positive comments about the location) who are more closely related to the query user is more likely to be the recommended result. Considering social information in the query can recommend more satisfactory results for users, this paper studies a new problem of semantic trajectory space keyword query: Social space Keyword Query based on semantic Trajectory (SKQT). This paper proposes a hybrid index structure that introduces social factors called Social Inverted Linear Quadtree (SIL-Quadtree) to improve the efficiency of SKQT query. The experiments use two datasets, Gowalla and Brightkite. The results show that the algorithm and index structure proposed in this paper perform better on running time and I/O.

The choice of activation functions in Convolutional Neural Networks (CNNs) is very important. Rectified Linear Unit (ReLU) has been widely-used in most CNNs. Recently, a series of non-monotonic activation functions gradually become the new standard to enhance performance of CNNs. Inspired by them, this paper firstly proposes a novel non-monotonic activation function called Power Function Linear Unit (PFLU). The negative part of PFLU is non-monotonic and closer to zero with the negative input decreasing, which can maintain sparsity of the negative part while introducing negative activation values and non-zero derivative values for the negative part. The positive part of PFLU does not use identity mapping but is closer to identity mapping with the positive input increasing, which can bring non-linearity property for the positive part. Next, this paper proposes faster PFLU (FPFLU). A wide range of classification experiments show that PFLU tends to work better than current state-of-the-art non-monotonic activation functions, and FPFLU can run faster than most non-monotonic activation functions.

Bayesian networks have many applications. Learning the optimal structure of a Bayesian network has always been important in this respect. In this paper, a bidirectional heuristic search algorithm is proposed for the order graph space commonly used in a Bayesian network. At the same time, heuristic functions that are admissible and consistent in terms of both forward and backward search are proposed to ensure convergence of the algorithm to the optimal solution. The experimental results show that, compared with traditional unidirectional heuristic search, in most cases, the bidirectional heuristic search proposed in this paper needs to expand fewer states, the convergence efficiency is higher, and less running time is needed.

Local Differential Privacy (LDP) can provide each user with strong privacy guarantees under untrusted data curators while ensuring accurate statistics derived from privatized data. Due to its powerfulness, LDP has been widely adopted to protect privacy in various tasks (e.g., heavy hitters discovery, probability estimation) and systems (e.g., Google Chrome, Apple iOS). In particular, ( ∊ , δ ) -LDP has been studied in related statistical tasks like private learning and hypothesis testing, but is mainly achieved by using Gaussian mechanism, leading to the limited data utility. In this paper, we investigate several novel mechanisms that achieve ( ∊ , δ ) -LDP with higher data utility in collecting and analyzing users’ data. Specifically, we first design two ( ∊ , δ ) -LDP algorithms for mean estimations on multi-dimensional numeric data, which can ensure higher accuracy than the optimal Gaussian mechanism. Then, we investigate different local protocols for frequency estimations on categorical attributes under ( ∊ , δ ) -LDP. Based on the proposed mechanisms, we further study on ( ∊ , δ ) -LDP-compliant stochastic gradient descent algorithms for machine learning models. Besides, the theoretical analysis of the error bound and the variance of the proposed algorithms are also presented in the paper. We have conducted extensive experiments on both real-world and synthetic datasets and demonstrated the high data utility of our proposed algorithms in the perspectives of simple data statistics tasks and complex machine learning tasks. The experimental results have shown that our proposed algorithms can effectively improve the data utility in different tasks while alleviating the privacy concerns of each individual.

This paper investigates the formation containment control under sampling and with time delays for multi-agent systems (MASs). First, a novel sampling control protocol for the MASs to achieve formation containment is proposed, where the communication among agents is only occurred at the sampling instance. Then the communication load and the waste of energy can be decreased significantly. In addition, time delays are considered in this paper. Second, by establishing an appropriate Lyapunov function, sufficient conditions for MASs with sampled data and time delays reaching formation containment are obtained by handling the established Lyapunov function. Finally, the obtained results are demonstrated by a simulation example.

The natural concept ontology structure of clothes has enabled easy management of large quantities of fashion images for online retailers and it is meaningful to study how to automatically recognize fashion images for both commercial promotion and academic research. In this paper, a new hierarchical approach is developed for large-scale fashion recognition. We first embed concept ontology into deep convolutional neural network (CNN) by adopting multiple deep CNN branches to learn node-specific features and classifiers explicitly. Then, we introduce a hierarchical knowledge distillation method to further improve the performance of fashion recognition. Finally, we employ the proposed approach for fashion recommendation. To deal with hierarchical deep learning constrains, we leverage back propagation to simultaneously refine the shared deep CNNs and the diverse CNN branches for relevant node features and classifiers by using our joint objective function. The main advantages of this paper lie in (1) providing an effective way for recognizing rich semantic explanations of fashion images without training large or multiple networks, and (2) saving the storage&time costs by learning personalized features and classifiers for each tree node. The experimental results on both our organized fashion dataset and the public DeepFashion dataset have verified the effectiveness and efficiency of the proposed approach on both hierarchical fashion recognition and within category fine-grained fashion recommendation.

For time series prediction, hybrid systems that combine linear and nonlinear models can provide more accurate performance than a single model. However, the irregularity of the error series and the unknown nature of combinations of different forecasters may strongly impact the performance of hybrid systems. Therefore, in this paper, we propose a novel method for time series prediction, in which error decomposition and a nonlinear combination of forecasters are introduced. The proposed method performs the following: (i) linear modeling to obtain the error series, (ii) error decomposition by using variational mode decomposition (VMD), (iii) nonlinear modeling and a phase fix procedure for the error subseries, and (iv) a combination of forecasters through an appropriate combination function generated by a nonlinear model. By using the proposed method, this paper constructs two hybrid systems, in which the autoregressive integrated moving average (ARIMA) is used for linear modeling, and two artificial intelligence (AI) models, namely, the multilayer perceptron (MLP) and support vector regression (SVR), are used for nonlinear modeling and combination, respectively. Finally, four time series data sets, six evaluation metrics, two single models and thirteen hybrid systems are used to assess the effectiveness of the proposed method. The empirical results show that hybrid systems based on error decomposition and a nonlinear combination of forecasters can achieve better performance than some existing systems and models.

Graph Neural Networks(GNNs) are powerful methods to analyze the non-Euclidean data. As a dominant type of GNN, Graph Convolutional Networks(GCNs) have wide applications. However, the analysis of the generalization error for GCNs with multilayer is limited. Based on the review of single-layer GCNs, this paper analyzes the generalization error of two-layers GCNs and extends the conclusion to the general GCNs models. Firstly, this paper examines two-layers GCNs and obtains the stability of the GCNs algorithm. And then, based on this algorithmic stability, the generalization stability of multilayer GCNs is obtained. This paper shows that the algorithmic stability of GCNs depends upon the graph filters and its product with node features as well as the training procedure. Furthermore, the generalization error gap of GCNs tends to be enlarged with more layers, which can interpret why GCNs with deeper layers have relatively poorer performance in test datasets.

Real-time pricing (RTP) is the pivotal component of demand response (DR) that promotes the power utilization of users in a cost-efficient way. This paper presents a reward fairness-based distributed RTP (RFbDRTP) framework for electric users to reduce the electricity consumption cost as well as experience the fairness from participating in DR. In RFbDRTP, a behavior welfare model (BWM) is developed to exploit the reward fairness strategy that returns the cost savings as a reward to the users in proportion to their load increase or decrease in DR. The model can motivate users to react to the price signal through adjusting their electricity consumption patterns, to in turn enable optimal distributed RTP for matching supply–demand. In this paper, users are assumed to interact with each other because of pricing based on the imbalance between load demand and electricity supply. We formulate the interactions among the users into a noncooperative game and give a sufficient condition to ensure the unique equilibrium in the game. After that, we develop a distributed algorithm and give a sufficient convergence condition of the algorithm. The simulation results show that the proposed RFbDRTP is effective in motivating users to participate in DR and matching demand with supply, and the distributed algorithm can converge to the equilibrium with a significant convergence rate.

Recently, a common starting point for solving complex unsupervised image classification tasks is to use generic features, extracted with deep Convolutional Neural Networks (CNN) pretrained on a large and versatile dataset (ImageNet). However, in most research, the CNN architecture for feature extraction is chosen arbitrarily, without justification. This paper aims at providing insight on the use of pretrained CNN features for image clustering (IC). First, extensive experiments are conducted and show that, for a given dataset, the choice of the CNN architecture for feature extraction has a huge impact on the final clustering. These experiments also demonstrate that proper extractor selection for a given IC task is difficult. To solve this issue, we propose to rephrase the IC problem as a multi-view clustering (MVC) problem that considers features extracted from different architectures as different "views" of the same data. This approach is based on the assumption that information contained in the different CNN may be complementary, even when pretrained on the same data. We then propose a multi-input neural network architecture that is trained end-to-end to solve the MVC problem effectively. This approach is tested on nine natural image datasets, and produces state-of-the-art results for IC., Comment: 21 pages, 16 figures, 10 tables, preprint of our paper published in Neurocomputing

Analyzing the runtime behaviors of Android apps is crucial for malware detection. In this paper, we attempt to learn the behavior level features of an app from function calls. The challenges of this task are twofold. First, the absence of function attributes hinders the understanding of app behaviors. Second, the graphical representation of function calls cannot be directly processed by classical machine learning algorithms. In this paper, we develop two methods to overcome these challenges. Based on function embedding, we first propose the concept of enhanced function call graphs (E-FCGs) to characterize app runtime behaviors. We then develop a Graph Convolutional Network (GCN) based algorithm to obtain vector representations of E-FCGs. Extensive experiments show that the features learned by our method can achieve surprisingly high detection performance on a variety of classifiers (e.g., LR, DT, SVM, KNN, RF, MLP and CNN), significantly outperforming the traditional static features.

Inspired by the recurrent highway networks, we study the coupled networks as a modular behavior of the networks, which can better improve the performance of the system. For a neural network, the non-zero continuous attractors play an important role to decode the information. The emphasis of this paper is to study the conditions for the generation of non-zero continuous attractors in the coupled new system theoretically. By exploring the relationship between network parameters, the conditions for generating non-zero continuous attractors in the new model are successfully determined. In order to verify the correctness and validity of the proposed conclusions, the results of this paper are further verified by simulation.