Search

Graph-based sparsity learning is one of the most successful unsupervised feature selection methods that has been widely adopted in many real-world applications. However, traditional graph-based unsupervised feature selection methods have several drawbacks: (1) being time-consuming and unable to deal with large-scale problems; (2) having difficulty tuning the regularization parameter with the sparsity regularization term; and (3) being unable to find explicit solutions owing to the limitation of sparsity, that is, feature selection with the ℓ 2 , 1 -norm constrained problem. Thus, this paper proposes OLPPFS, a method to preserve the local geometric structure within the feature subspace by imposing the ℓ 2 , 0 -norm constraint. First, the linear mapping capability of the proposed model is enhanced using locality-preserving projections (LPPs), whichpreserve the local and global geometric manifold structure of the data while enhancing the ability to reconstruct data. Second, the graph-embedding learning method can accelerate the construction of a sparsity affinity graph and describe the intrinsic structure of the dataset well. More importantly, we propose a method for solving a projection matrix with the ℓ 2 , 0 -norm constrained, which can accurately select a explicit group of discriminative feature subsets. This method can yield a more accurate sparse projection matrix than the ℓ 2 , 1 -norm. We also adopt FOLPPFS, an effective anchor-based strategy to further accelerate our model with two flexible options. Extensive experiments on eight datasets demonstrate that the proposed method is superior to the other methods and can preserve a better local geometric structure of the dataset with less time consumption. [ABSTRACT FROM AUTHOR]

• Propose to explore two kinds of topic signals and tailor them to rumor detection. • Propose a multi-task learning strategy and jointly train the model on both topic credibility prediction and user credibility prediction. • Experimental results demonstrate our model outperforms all state-of-the-art methods. Detecting rumors on social media and preventing its spread play a critical role for politics, economy, etc. Conventional studies mainly focus on exploiting the content or context of the source post, while they always ignore the rich topic information within the source post. To tackle this issue, in this paper, we propose a Topic and Structure Aware Neural Network (TSNN) for rumor detection. To be specific, we explore two kinds of topic signals, including a coarse-grained topic signal (i.e., topic credibility) and a fine-grained topic signal (i.e., latent topic representation), and tailor them to the task of rumor detection. Moreover, we introduce a new auxiliary task, i.e., topic credibility prediction, in order to effectively leverage the rich topic information within source posts. Finally, we develop a multi-task learning strategy that helps improve rumor detection performance by jointly learning the task of topic credibility prediction and user credibility prediction. Extensive experiments on three real-world datasets demonstrate that the proposed approach TSNN is superior to the state-of-the-art baseline methods. [ABSTRACT FROM AUTHOR]

This paper presents a federated learning approach based on utilizing computational resources of the IoT edge devices for training deep neural networks. In this approach, the edge devices and the cloud server collaborate in the training phase while preserving the privacy of the edge device data. Owing to the limited computational power and resources available to the edge devices, instead of the original neural network (NN), we suggest to use a smaller NN generated using a proposed heuristic method. In the proposed approach, the smaller model, which is trained on the edge device, is generated from the main NN model. By the exploiting Knowledge Distillation (K D) approach, the learned knowledge in the server and the edge devices can be exchanged, leading to lower required computation on the server and preserving data privacy of the edge devices. Also, to reduce the knowledge transfer overhead on the communication links between the server and the edge devices, a method for selecting the most valuable data to transfer the knowledge is introduced. The effectiveness of this method is assessed by comparing it to state-of-the-art methods. The results show that the proposed method lowers the communication traffic by up to 250 × and increases the learning accuracy by an average of 8.9 % in the cloud compared to the prior K D -based distributed training approaches in CIFAR-10 dataset. [ABSTRACT FROM AUTHOR]

Neural responding variability to the same stimulus typically decreases after a stimulus presented. During neural variability quenching, the pre-stimulus neural activities interact with the post-stimulus neural responses. However, whether these interactions have influences on information coding remains unclear. In this paper, we construct a two-layer k-winner-take-all (k-WTA) spiking network which simulates primary visual cortical neural responses through probabilistic inference. Generating the phenomenon of neural variability quenching, the network could reflect interactions between pre- and post-stimulus neural responses consistent with experimental observations. During neural variability quenching, pre-stimulus neural responding variability and complexity are considered as factors for the post-stimulus neural responses. Simulations to given stimuli are classified with each varying factor, respectively. Neural responding dimensionality measures the capacity of information coding to given stimuli. Over classified simulations, both of two factors could modify interactions between pre- and post-stimulus neural responses, leading to different neural responding dimensionalities. During neural variability quenching, the temporal structure of stimuli performs as another factor which also could modify neural interactions and induce the varying neural responding dimension. Our model provides the possible interpretation to how the pre-stimulus neural responses participate in neural variability quenching and affect the information coding. [ABSTRACT FROM AUTHOR]

Reconstructing natural image from its corresponding compressive sensing (CS) measurements is an ill-posed problem. Learning accurate prior of desirable image is essential to solve this inverse problem in high quality, especially for CS reconstruction from noisy measurements. The existing learning-based methods cannot effectively simulate whole potential noise in the testing data during external learning, and cannot effectively exploit the information from internal testing data. In this paper, we present an effective convolutional neural network (CNN) based method for CS reconstruction from noisy measurements, which learns the deep prior from an external dataset and internal noisy testing data with Stein's unbiased risk estimator (SURE). Specifically, we first pre-train an arbitrary CNN for CS reconstruction with an external dataset to learn a common prior. Then, we utilize meta learning to find a generic initial parameter that is suitable for fast internal learning and adaption to various noisy measurements. Finally, we customize the learned network to learn a specific prior for each internal testing data under Gaussian noise or more general mixed Poisson-Gaussian noise. Experimental results show that the proposed method outperforms the state-of-the-art methods under both comprehensively quantitative metrics and perceptive quality. [ABSTRACT FROM AUTHOR]

Session-based recommendation aims to predict a user's next action based on a series of anonymous sequences and plays an essential role in various online applications, such as e-commerce and music applications. Recently, transformer-based models have obtained results that are competitive with or even surpass those of recurrent neural networks, because of the good performance of transformer models in capturing long-distance dependencies. However, a transformer has a limited ability to mine local contextual information, which can be regarded as collective features. Researchers are seeking to address this limitation by augmenting the contextual transition to boost session representation learning. Accordingly, in this paper, we enhance the capabilities of a transformer in a session-based recommendation task by introducing convolutional neural networks (CNNs) at the stage of aggregating the item features with long- and short-distance dependencies. We first borrow a self-attention module from the classic transformer model to explore the long-distance dependencies. We next propose horizontal and vertical convolutions for enhancing the local collective information and then obtain a session representation by integrating the two types of features. Extensive experiments on real-world datasets show that our method outperforms those that rely on a transformer or a CNN alone. [ABSTRACT FROM AUTHOR]

Filter pruning has drawn extensive attention due to its advantage in reducing computational costs and memory requirements of deep convolutional neural networks. However, most existing methods only prune filters based on their intrinsic properties or spatial feature maps, ignoring the correlation between filters. In this paper, we suggest the correlation is valuable and consider it from a novel view: the frequency domain. Specifically, we first transfer features to the frequency domain by Discrete Cosine Transform (DCT). Then, for each feature map, we compute a uniqueness score, which measures its probability of being replaced by others. This way allows to prune the filters corresponding to the low-uniqueness maps without significant performance degradation. Compared to the methods focusing on intrinsic properties, our proposed method introduces a more comprehensive criterion to prune filters, further improving the network compactness while preserving good performance. In addition, our method is more robust against noise than the spatial ones since the critical clues for pruning are more concentrated after DCT. Experimental results demonstrate the superiority of our method. To be specific, our method outperforms the baseline ResNet-56 by 0.38 % on CIFAR-10 while reducing the floating-point operations (FLOPs) by 47.4 %. In addition, a consistent improvement can be observed when pruning the baseline ResNet-110: 0.23 % performance increase and up to 71 % FLOPs drop. Finally, on ImageNet, our method reduces the FLOPs of the baseline ResNet-50 by 48.7 % with only 0.32 % accuracy loss. [ABSTRACT FROM AUTHOR]

As a classical machine learning model, support vector machine (SVM) has attracted much attention due to its rigorous theoretical foundation and powerful discriminative performance. The doubly regularized SVM (DRSVM) is an important variant of SVM based on elastic-net regularization, which considers both the sparsity and stability of the model. To tackle the problems of explosive increases in data dimensions and data volume, the alternating direction method of multipliers (ADMM) algorithm can be used to train the DRSVM model. ADMM is an effective iterative algorithm for solving convex optimization problems by decomposing a large issue into a series of solvable subproblems, which is also well suited for distributed computing. However, lack of guaranteed convergence and slow convergence rate are two critical limitations of ADMM. In this paper, a 3-block ADMM algorithm based on the over-relaxation technique is proposed to accelerate DRSVM training, namely, the over-relaxed DRSVM (O-RDRSVM). The main strategy of the over-relaxation technique is to further append the information from the previous iteration to the next iteration to improve the convergence of ADMM. We also propose a distributed version of O-RDRSVM to handle parallel and distributed computing faster, termed DO-RDRSVM. Moreover, we develop a fast O-RDRSVM algorithm (FO-RDRSVM) and a fast DO-RDRSVM algorithm (FDO-RDRSVM), which further reduce the computational cost of O-RDRSVM and DO-RDRSVM by employing the matrix inversion lemma. The convergence analyses ensure the effectiveness of our algorithms for DRSVM training. Finally, extensive experiments on public datasets demonstrate the advantages of our algorithms in terms of convergence rate and training time while maintaining accuracy and sparsity comparable to those of previous works. [ABSTRACT FROM AUTHOR]

Identifying influential nodes in social networks is a fundamental task. Due to the development of Graph Neural Networks, Graph Convolution Network (GCN) based model has been introduced to solve this problem. Compared to traditional methods, the existing GCN-based models are more accurate in identifying influential nodes because they can better aggregate the multi-dimension features. However, the GCN-based method treats this problem as a binary classification task rather than a regression task, making it less practical. To make the GCN-based model more practical, we treat identifying influential nodes as a regression task. Moreover, when aggregating neighbor features, GCN ignores the difference in neighbor importance, which will affect the prediction performance of the GCN-based models. This paper proposes a graph multi-head attention regression model to address these problems. Vast experiments on twelve real-world social networks demonstrate that the proposed model significantly outperforms baseline methods. To the best of our knowledge, this is the first work to introduce the multi-head attention mechanism to identify influential nodes in social networks. [ABSTRACT FROM AUTHOR]

This paper investigates the generalized Nash equilibrium searching problem of multi-agent games over weight-unbalanced directed networks. In this problem, the feasible action set of each agent is not only constrained by private convex sets and shared coupling equality, but also constrained by its own uncertain dynamics. Moreover, the local cost function is related to both his own actions and others, and each agent is only allowed access to neighbor information. To address this problem, we propose a neuro-adaptive control strategy based on two-stage design. In the first stage of design process, an approximator with adaptive-gain is designed to generate a virtual trajectory that converges to a necessary Nash equilibrium, the compensator based on consensus-tracking is used to obtain non-neighbor information and several auxiliary state variables are used to exchange information with local neighborhoods on a digraphs to deal with equality constraints. In the second stage of the strategy, we further developed a neuro-adaptive tracking controller based on one-step design for tracking the virtual trajectory. In the controller design, the virtual control variables and the actual control laws are obtained in a collective way, without repeating the design process. We introduce a variable called the minimum learning parameter to reduce the number of online learning parameters of the neural network. By using tools from variational inequality theory and Lyapunov stability theory, we prove that the proposed control strategy can drive all agents reach Nash equilibrium. Finally, the effectiveness of control strategy is verified by simulation example. [ABSTRACT FROM AUTHOR]

Sample efficiency, which refers to the number of samples required for a learning agent to attain a specific level of performance, is central to developing practical reinforcement learning (RL) for complex and large-scale decision-making problems. The ability to transfer and generalize knowledge gained from previous experiences to downstream tasks can significantly improve sample efficiency. Recent research indicates that successor feature (SF) RL algorithms enable knowledge generalization between tasks with different rewards but identical transition dynamics. It has recently been hypothesized that combining model-based (MB) methods with SF algorithms can alleviate the limitation of fixed transition dynamics. Furthermore, uncertainty-aware exploration is widely recognized as another appealing approach for improving sample efficiency. An agent can efficiently explore to better understand an environment by tracking uncertainty about the value of each available action. Putting together two ideas of hybrid model-based successor feature (MB-SF) and uncertainty leads to an approach to the problem of sample efficient uncertainty-aware knowledge transfer across tasks with different transition dynamics or/and reward functions. In this paper, the uncertainty of the value of each action is approximated by a Kalman filter (KF)-based multiple-model adaptive estimation. This KF-based framework treats the parameters of a model as random variables. To the best of our knowledge, this is the first attempt at formulating a hybrid MB-SF algorithm capable of generalizing knowledge across large or continuous state space tasks with various transition dynamics while requiring less computation at decision time than MB methods. We highlight why previous SF-based methods are constrained to knowledge generalization across same transition dynamics, present our novel approach on a firm theoretical foundation, and design a set of demonstration tasks to empirically validate the effectiveness of our proposed approach. The number of samples required to learn the tasks was compared to recent SF and MB baselines. The results show that our algorithm generalizes its knowledge across different transition dynamics, learns downstream tasks with significantly fewer samples than starting from scratch, and outperforms existing approaches. We believe that our proposed framework can account for the computationally efficient behavioural flexibilities observed in the empirical literature and can also serve as a solid theoretical foundation for future experimental work. [ABSTRACT FROM AUTHOR]

• We propose a new graph convolution network with subgraph embedding. • It extracts local information with subgraphs partitioned by Girvan Newman algorithm. • Experiments confirm the superiority of predicting mutagenicity in aromatic hydrocarbons. • The accuracy is verified with comparison of nine SOTA deep learning models. • The proposed method prevents about 15 %p of GCN's information dilution. An aromatic hydrocarbon refers to an organic material having a carbon ring such as benzene and a functional group in the carbon ring. As the industry develops, natural pollution becomes harsh, new compounds emerge, and the exposure to aromatic hydrocarbons is continuously increasing. Predicting mutagenicity is one of the crucial issues in reducing the risk because these organisms may have properties that penetrate the DNA of living things to cause mutations. Recently, the accuracy of mutation prediction has improved due to the power of deep learning. However, most conventional methods do not consider the characteristics of molecular aromatic hydrocarbons, which dilutes local information and results in a severe deterioration of the prediction performance. In this paper, we propose a method of exploiting subgraph convolution neural networks that enables the extraction of local information of a graph by partitioning it to maintain the detailed information. For extracting the features of molecules, we use the Girvan Newman algorithm to partition the graph according to the carbon ring and functional group and obtain the embedding vectors of the subgraphs as well as the original graph with graph convolution network (GCN). The embedding vectors are combined to represent the whole graph information and predict mutagenicity. Experiments with MUTAG, NCI1 and NCI109, datasets for predicting mutagenicity of molecules in graph structure, confirm that we successfully segment carbon rings and functional groups from molecular graphs and predict mutations using the partitioned graphs, leading to a 2 %p performance improvement. In addition, the proposed method has prevented about 15 %p of information dilution in GCN, and an analysis of the latent space of graphs reveals that the subgraphs extracted maintain the local information appropriately. [ABSTRACT FROM AUTHOR]

Visualizations are powerful tools that are commonly used by data scientists to get more insights about their high dimensional data. One can for example cite t -SNE, which is probably one of the most famous and widely-used visualization techniques. However, t -SNE is a nonlinear and non-parametric technique that makes it suffer from a lack of interpretability. In this paper, we present a new technique inspired by t -SNE's objective function that combines its ability to build nice visualizations with the interpretability of decision trees. This new visualization technique, called DT-SNE, can be seen as a discrete visualization technique where groups of instances are provided, as well as a ranking between them. The decision rules of the decision tree provide clear insights to interpret these different groups. [ABSTRACT FROM AUTHOR]

Although tremendous strides have been made in object recognition over large-scale 3D point clouds, one of the remaining open challenges is detecting tiny objects. The signal and appearance information of tiny objects are generally sparse and insufficient due to their tiny size, which makes the tiny object difficult to be detected with existing studies both in tiny 2D object recognition and general 3D object recognition since 3D topology relations are lost due to feature projection in tiny 2D object recognition and massive background may dominate the feature learner in general 3D object recognition. To the best of our knowledge, we explore tiny object recognition for the first time over large-scale 3D point clouds by designing deep neural network. To cope with this problem, a novel two-stage approach is proposed in this paper, which can effectively learn an informative and discriminative feature representation and efficiently process large-scale point clouds. Specifically, a class-aware filtering strategy is designed to dispense with the redundant background information. After that, we introduce a novel aggregating and sampling scheme in a supervised manner to progressively increase the receptive field for each 3D point, which can adaptively capture useful signals from tiny objects and learn complex geometric structures. Last, we propose a biased loss function that is inversely correlated to the number of tiny object points, thereby effectively handling the sparsity of tiny objects. Extensive experimental results over two real-world data sets validate the effectiveness and efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) data are produced in quantity for measuring brain activity in response to external stimuli. With the rapid development of brain-inspired intelligence, spiking neural network (SNN) possesses the potential to handle EEG data by using spiking activity transmitted among spatially located synapses and neurons. As an original and unifying SNN architecture, NeuCube, is developed to model, recognize and understand EEG data. However, the NeuCube still faces some challenges for EEG-based pattern recognition, such as few labeled data and changes of data probability distribution. Hence, this paper proposes a novel method to improve the performance of the NeuCube for EEG-based pattern recognition by transfer learning. In the first place, the covariance matrix alignment of EEG data is implemented for every subject in the Euclidean space, which reduces the probability distribution discrepancy of EEG data between different subjects. Different estimation methods for reference covariance matrix are tested and the optimal one is selected for different subjects. Secondly, spatio-temporal features of EEG data are extracted based on the NeuCube reservoir. Since hyper-parameters of the NeuCube reservoir have a great impact on its spatio-temporal representation, an improved cuckoo search algorithm is proposed to discover the optimal hyper-parameters for obtaining the optimal spatio-temporal features. Last but not least, a weighted transfer support vector machine is proposed to improve the original output classifier of the NeuCube in order to make the model adaptive to the cross-domain variability of EEG data. The proposed method is tested on open dataset 2a from BCI competition IV 2008 and achieves good spatio-temporal pattern recognition results. Furthermore, the neuron connectivity and activation level associated with the process of mental tasks are illustrated. [ABSTRACT FROM AUTHOR]

Metric learning has attracted significant attention due to its high effectiveness and efficiency for pattern recognition task. Traditional supervised metric learning algorithms attempt to seek a global distance metric with labeled samples. When data are represented with multimodal and only limited supervision information is available, these approaches are insufficient to obtain satisfactory results. In this paper, we develop a robust semi-supervised multi-metric learning method (RSMM) to improve classification performance. The proposed RSMM learns multiple local metrics and a background metric instead of a single global metric. Specifically, we divide the metric space into influential regions and background region, and then regulate the effectiveness of each local metric to be within the related regions. Simultaneously, a geometrically interpretable, symmetric distance is defined with local metrics and background metric. Based on the resultant learning bounds, we obtain the regularization term to improve the classifier's generalization ability. Moreover, the manifold regularization term is introduced to preserve the supervision information as well as geometry structure. The substantial unlabeled samples may cause potential threats and large uncertainties, so the logarithmic loss function is utilized to enhance the robustness. An efficient gradient descent algorithm is exploited to solve the non-convex challenging problem. To further understand the proposed algorithm, we theoretically derive its robustness and generalization error bounds. Finally, numerical experiments on UCI datasets and image datasets demonstrate the feasibility and validity of the RSMM. [ABSTRACT FROM AUTHOR]

Traditional recommenders suffer from hidden confounding factors, leading to the spurious correlations between user/item profiles and user preference prediction, i.e., the confounding bias issue. Most works resort to only one confounding bias, which greatly block their applications on recommendations with mixture confounder, i.e., more than one bias. It is therefore of practical demand to empower the recommender with the capability of debiasing different biases from data. Moreover, the positive effect of bias is neglected in most previous works. We argue that confounding bias is actually beneficial for capturing users' preferences in some recommendation scenarios. In this paper, we propose a novel deconfounded causal learning method called GCRec (G raph C ausal Rec ommendetion) to debias two confounders: social network confounder and item group confounder. We employ Graph Neural Networks (GNNs) to aggregate user-user connections for social networks and user-item interactions for item groups in order to learn high-order representations that can efficiently debias these two confounders from a causal view. In the inference stage, we use symmetric Kullback–Leibler divergence to measure the user preference drift. If the divergence is large, we perform the causal intervention to alleviate the bias amplification caused by confounders on user preferences. Otherwise, we incorporate the user preferences that can potentially deliver a positive effect on favoring recommendation performance. Extensive experiments are conducted on two benchmark datasets to verify that GCRec outperforms state-of-the-art methods and achieves robust recommendations. [ABSTRACT FROM AUTHOR]

[Display omitted] • We propose a black-box adversarial text generation scheme called TextGuise, which can be used for almost all text classification tasks. The experiments show that TextGuise is superior to the state-of-the-art text adversarial example generation methods in terms of its attack success rate and attack efficiency when the perturbation ratio does not exceed 0.2.The adversarial examples generated using TextGuise retain the semantic information and strong readability of the text. None of the current defense methods can effectively defend against TextGuise. Adversarial examples greatly compromise the security of deep learning models. The key to improving the robustness of a natural language processing (NLP) model is to study attacks and defenses involving adversarial text. However, the current adversarial attack methods still face problems, such as the low success rates of attacks on some datasets, and the existing defense methods can already successfully defend against some attack methods. As a result, such attacks are unable to dig deeper into the flaws of NLP models to inform further defense improvements. Hence, it is necessary to design an adversarial attack method with a wider attack range and stronger performance. Aiming at the advantages and disadvantages of existing methods, this paper proposes a new adaptive black-box text adversarial example generation scheme, TextGuise. First, we design a keyword selection method in which word scores are calculated by combining context semantics to select the appropriate keywords to modify. Second, to maintain semantics, new keyword substitution rules are designed in combination with the characteristics of text and popular text expressions. Finally, the best modification strategy is adaptively selected through a querying model to reduce the magnitudes of disturbances. TextGuise can automatically select replacement keywords and replacement strategies that efficiently generate adversarial examples with good readability for various text classification tasks. Attack experiments conducted with TextGuise on 5 datasets yield high attack success rates that can surpass 80% when the perturbation ratio does not exceed 0.2. In addition, we present and discuss experiments focusing on defense, text similarity, query times, time consumption, etc., to test the attack performance of TextGuise. The results show that our attack method can achieve a good balance among various metrics. [ABSTRACT FROM AUTHOR]

As a powerful data modeling tool, Heterogeneous Information Network (HIN) has been successfully used in auxiliary information exploitation to boost recommendation performance. For HIN based recommendation, it is challenging to extract and fuse useful features of user preferences and item attributes under different semantic paths in HINs. Existing methods leverage a pre-defined fusion function to integrate different semantics for recommendation, which cannot characterize the complex nonlinear interactions between users and items. In this paper, we present a general framework named MNRec, short for Meta-path fusion based Neural Recommendation, to extract and fuse user and item embeddings under different meta-paths for recommendation. Under the framework, we propose an instantiation of MNRec with Multi-Layer Perceptron (MLP) structure. It consists of two major steps, i.e., meta-path based heterogeneous network embedding and deep learning based rating prediction. Concretely, appropriate meta-paths are first designed according to domain knowledge. Then the embeddings of users and items are obtained through a meta-path and commuting matrix based heterogeneous network embedding method. Finally, in light of the powerful nonlinear modeling capabilities of deep neural networks, the learned embeddings under different meta-paths are integrated into a two-pathway MLP structure for rating prediction. Experimental results on three real-world datasets demonstrate the superiority and effectiveness of MNRec compared with state-of-the-art baselines in rating prediction. [ABSTRACT FROM AUTHOR]

• A blind spot speckle suppression method based on a global awareness strategy is proposed to achieve self-supervised denoising of sonar images, which helps to reduce the noise interference to downstream tasks. • A hybrid contextual dynamic attention mechanism (HCDAM) is introduced to enhance and correct the locality map for salient region extraction to improve the reliability of segmented targets. • A co-training method for the joint speckle suppression task and the garbage instance segmentation task is presented, which facilitates the flexible execution of underwater garbage detection tasks. Sonar is widely used in marine water cleaning tasks, so sonar images have become an effective tool for garbage detection and underwater scene analysis. However, it is an extremely difficult task to achieve fully supervised denoising and garbage detection for sonar images. This is because sonar images are weakly annotated samples that are susceptible to noise interference and have no reference clean image. To this end, we propose a sonar image garbage instance segmentation model via global despeckling and dynamic attention graph optimization(GD-DAGO). Specifically, a self-supervised blind spot network denoising structure is presented in this paper. The proposed denoising model overcomes the defects of information loss in the traditional blind spot network structure and performs global awareness speckle suppression for the noise characteristics of sonar images themselves. In addition, a novel dynamic attention structure is employed to improve the target region estimation in the instance segmentation module and does not require supervision beyond image-level category labeling. Finally, in order to enhance the cooperative ability between the two tasks, we adopt a local perceptual loss strategy based on mask proposals guided by the downstream task, so that the whole model takes more into account the characteristics of sonar images and better serves the sonar garbage detection task. Experimental results on ARACATI 2017 and marine-debris-fls-datasets (MDFD) show that the proposed algorithm achieves a performance gain of 0.4218 and 4.2% in terms of denoising effect (ENL) and detection accuracy ( AP 25 ), respectively, compared with suboptimal algorithms. [ABSTRACT FROM AUTHOR]

Monocular 3D object detection aims to localize objects in 3D space from a single image. This is a difficult problem due to the lack of accurate depth measurements. Many methods predict depths upfront using a pre-trained vision-based depth estimator to assist in 3D object detection. However, the methods show limited improved performances because of the depth inaccuracy and the neglect of depth confidence. In this paper, we propose a new end-to-end 3D object detection framework by combining a monocular camera with a cheap 4-beam LiDAR. The minimal LiDAR signal is leveraged as an additional input to predict high-quality and dense depth maps from monocular images. Meanwhile, several 3D proposals are generated by a keypoint-based detector. The key challenge is encoding the depth confidence to capture the depth estimation uncertainty. Therefore, we propose probabilistic instance shape reconstruction to exploit instance shape information for box refinement. Our method employs a fully differentiable end-to-end framework, making it simple and efficient. The experimental results on the KITTI dataset demonstrate that the proposed method achieves state-of-the-art performance, thus validating the effectiveness of the sparse LiDAR data and the probabilistic instance shape reconstruction. Code is available at https://github.com/xjtuwh/SparseLiDAR_fusion. [ABSTRACT FROM AUTHOR]

• Optimal location of interurban electric vehicle charging station infrastructure. • Multi-objective genetic algorithm to improve stalls utility and stations coverage. • Experimental results in the USA improve the current infrastructure. In recent years, there has been a strong desire to meet the challenge of electrification of vehicles in order to achieve the decarbonization objective. However, as sales of electric vehicles have increased, there is a significant lack of infrastructure to support the charging of this type of vehicle. The infrastructural deficiencies are even more evident in the interurban environment, where the autonomy in kilometers of the battery is a critical issue. To minimize the substantial economic costs involved in installing sufficient charging points to ensure any interurban journey, it is necessary to establish mechanisms that evaluate appropriate locations to deploy the necessary stations. Accordingly, this paper proposes using an evolutionary approach to calculate the most suitable locations in an interurban environment for electric charging stations. For this purpose, different input information is taken into account in the allocation process. The proposed algorithm has been tested using real data from the USA. The results assess the current infrastructure and show the advantages of the locations proposed by the algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we present a Q-learning framework for solving finite-horizon zero-sum game problems involving the H ∞ control of linear system without knowing the dynamics. Research in the past mainly focused on solving problems in infinite horizon with completely measurable state. However, in the practical engineering, the system state is not always directly accessible, and it is difficult to solve the time-varying Riccati equation associated with the finite-horizon setting directly either. The main contribution of the proposed model-free algorithm is to determine the optimal output feedback policies without measurement state in finite-horizon setting. To achieve this goal, we first describe the Q-function caused by finite-horizon problems in the context of state feedback, then we parameterize the Q-functions as input–output vectors functions. Finally, the numerical examples on aircraft dynamics demonstrate the algorithm's efficiency. [ABSTRACT FROM AUTHOR]

In most Internet of Things (IoT) scenes, data missing can be unavoidable when huge number of smart devices are collecting data uninterruptedly. Therefore, data imputation can be an integral part of pre-processing before data mining. It is widely known that IoT time series show strong dependencies in both spatial and temporal dimension, and the spatial relation among the devices is in non-euclidean space. However, most machine-learning-based and deep-learning-based approaches either only take temporal features into account or only catch spatial features in euclidean space. In this paper, we propose a novel network as ST-VAE (Spatio-Temporal Variational Auto-Encoder) to address the problem above. Our architecture is mainly based on Variational Auto-Encoder (VAE). Specifically, two kinds of VAE are utilized. One is for calculating the adjacent matrix of device network which is the essential input of GCN, and the other is for data imputation task based on the spatial and temporal dependencies. Experiments conducted on different real-world and public datasets demonstrate that our ST-VAE can not only populate the missing spatio-temporal data accurately but also outperforms other state-of-art approaches from the whole. [ABSTRACT FROM AUTHOR]

This paper studies the cluster consensus problem for networks with antagonistic interactions modelled by adjacency matrices with negative weights. By introducing an extended digraph representation consisting of purely cooperative interactions with lifting approach, we relate the trajectories of the system to those of an extended system with a positive digraph. The behaviours of agents in a signed network are extracted from its extended digraph. Consequently, the number of clusters and the cluster members are explicitly determined for any signed digraph by using primary and secondary layer subgraph concepts. The relation between the dynamics of a signed system and its extended representation is investigated for first and higher-order systems. The conditions that make both systems stable are stated. Additionally, the control parameters to achieve cluster consensus are derived explicitly for first, second and third order systems. The obtained results for continuous-time networks are subsequently extended to discrete-time networks. Finally, theoretical results are illustrated via numerical examples. [ABSTRACT FROM AUTHOR]

The difficulties in both data acquisition and annotation substantially restrict the sample sizes of training datasets for 3D medical imaging applications. Therefore, it is non-trivial to build well-performing 3D convolutional neural networks from scratch. Previous efforts on 3D pre-training have frequently relied on self-supervised approaches, which use either predictive or contrastive learning on unlabeled data to build invariant 3D representations. However, because of the unavailability of large-scale supervision information, obtaining semantically invariant and discriminative representations from these learning frameworks remains problematic. In this paper, we revisit an innovative yet simple fully-supervised 3D network pre-training framework to take advantage of semantic supervision from large-scale 2D natural image datasets. With a redesigned 3D network architecture, reformulated natural images are used to address the problem of data scarcity and develop powerful 3D representations. Comprehensive experiments on five benchmark datasets demonstrate that the proposed pre-trained models can effectively accelerate convergence while also improving accuracy for a variety of 3D medical imaging tasks such as classification, segmentation, and detection. In addition, as compared to training from scratch, it can save up to 60% of annotation efforts. On the NIH DeepLesion dataset, it also achieves state-of-the-art detection performance, outperforming earlier self-supervised and fully-supervised pre-training approaches, as well as methods that do training from scratch. To facilitate further development of 3D medical models, our code and pre-trained model weights are publicly available at https://github.com/urmagicsmine/CSPR. [ABSTRACT FROM AUTHOR]

In this paper, the asymptotic synchronization of Riemann–Liouville fractional delayed memristive neural networks is explored. Firstly, in order to achieve the control target more effectively and economically, a new type of event-based hybrid impulsive controller is designed. In addition, through inequality techniques and impulse analysis methods, some sufficient criteria for asymptotic synchronization are obtained by constructing new Lyapunov–Krasovskii functionals. At the same time, it is verified that Zeno behavior could be eliminated under the given trigger conditions in the error system. It should be noted that some results based on algebraic inequalities fill in the gaps of existing ones and our controller is more practical and energy-saving. Lastly, a simulation instance is depicted to verify the validity and correctness of the submitted conclusions. [ABSTRACT FROM AUTHOR]

This paper concerns the anti-synchronization for master–slave Markovian neural networks (NNs), in which a more general Markovian chain with uncertain transition probability is introduced to the controller of slave NNs. An asynchronous intermittent control scheme is proposed to achieve the anti-synchronization, which not only overcomes the problem that the jumping information of the system mode is not available for the controller instantly, but also strikes a balance between control cost and accuracy. Then, sufficient conditions are established to guarantee the anti-synchronization of the master–slave Markovian NNs according to the Lyapunov stability method and the iteration method. Finally, the effectiveness of the proposed asynchronous intermittent control method is verified by means of simulation examples. [ABSTRACT FROM AUTHOR]

This paper studies an adaptive critic design (ACD) solution based on the event-driven mechanism for the constrained state and input system with external disturbance. At first, the barrier function is presented to construct the transformation of the constrained state system, and then, a suitable value function with non-quadratic utility function is designed according to the auxiliary system to acquire the control sequence in the infinity domain. After that, the comprehensive problem is transited into solving the Hamilton–Jacobi-Isaacs (HJI) equation. Then, the optimal control policy pair is obtained by policy iteration (PI) via double event-driven scheme. The three critic, action and disturbance neural networks (NNs) are built up to manipulate the data online concurrently to approximate the control pair sequence, and the ultimately uniformly bounded (UUB) proof of the estimation error generated by NNs is given. The last but not least, two sets of contrast simulations are analyzed to demonstrate the effectiveness of the proposed algorithm, which makes the model reduce the data transmission density and decrease the update times of control policies under the premise of system stability and ideal performance. [ABSTRACT FROM AUTHOR]

A kernel-based intuitionistic weight fuzzy k-modes algorithm (KIWFKM) is proposed in this paper which can improve the clustering performance of categorical data. The current FKM algorithm which were proposed by researchers generally have three drawbacks. Firstly, the algorithms were easily limited to the local optimal solution. Secondly, most of algorithms were considering all attributes equally. Thirdly, most algorithms are sensitive to noise data points. So the intuitionistic fuzzy sets (IFS), kernel trick and weight concept are introduced into the objective function which can not only solve the problem of all attributes equally but also improve the robustness to noise. In addition, a coupled DCP (chained tissue-like P system combines DNA genetic rules) system is established which is used for realizing the KIWFKM algorithm (KIWFKM-DCP). The uncertainty and implicit parallelism of the DCP system can help the KIWFKM algorithm jump out of the local optimal solution and find better solution. Finally, we conduct experiments and compare experiment results with six state-of-the-art clustering methods. Experimental results conduct that the KIWFKM-DCP algorithm perform better than the other comparison clustering algorithms. [ABSTRACT FROM AUTHOR]

• Introduces the novel task of Sexual Facial Expression Recognition (SFER). • Triple-BigGAN; a conditional GAN with a generator, discriminator, and classifier. • SEA-Faces-30k; a new dataset with Erotic, Suggestive-Erotic, and Non-Erotic classes. • Evaluation using FER-2013, ExpW, MNIST, CIFAR-10, SVHN, and SEA-Faces-30k datasets. Automatic recognition of facial images showing erotic expressions can help to understand our social interaction and to detect non-appropriate images even when there is no nakedness present in them. This paper contemplates, for the first time, to exploit facial cues applied to automatic Sexual Facial Expression Recognition (SFER). With this goal, we introduce a new dataset named Sexual Expression and Activity Faces (SEA-Faces-30k) for SFER, which contains 30k manually labeled images under three categories: erotic, suggestive-erotic, and non-erotic. Deep Convolutional Neural Networks require large-scale annotated image datasets with diversity and variations to be properly trained. Unfortunately, gathering such a massive amount of data is not feasible in this area. Therefore, we present a new semi-supervised GAN framework named Triple-BigGAN, which learns a generative model and a classifier simultaneously. It learns both tasks in an end-to-end fashion while using unlabeled or partially labeled data. The Triple-BigGAN framework shows promising classification performance for the SFER task (i.e., 93.59 %) and other five benchmark datasets, i.e., FER-2013, CIFAR-10, Expression in-the-Wild (ExpW), Modified National Institute of Standards and Technology database (MNIST), and Street View House Numbers (SVHN). Next, we evaluated the quality of samples generated by Triple-BigGAN with a resolution of 256 × 256 pixels using Inception Score (IS) and Frechet Inception Distance (FID). Our approach obtained the best FID (i.e., 19.94 %) and IS (i.e., 97.98 %) scores on the SEA-Faces-30k dataset. Further, we empirically demonstrated that synthetic erotic face images generated by Triple-BigGAN could also help in improving the classification performance of deep supervised networks. [ABSTRACT FROM AUTHOR]

Active contour models (ACMs) are popular and widely used for many image segmentation applications and obtain promising results. However, these methods are unable to achieve the highest performance in the presence of intensity inhomogeneity. To address this issue, this paper presents an ACM based on the combination of a convolutional neural network (CNN) and a texture descriptor approach. This study uses a CNN model to generate parameter maps more effectively for ACM. Compared to conventional global techniques, these parameter maps increase the speed of movement of the contour into the target. In this approach, the Local Word Directional Pattern (LWDP) is applied as the texture descriptor. LWDP is a texture descriptor that uses the angle between two gradients for exploring the texture structure inside the image. In the proposed method both the original image and the new image obtained by the LWDP texture descriptor (encoded image) are provided as inputs to the CNN. The experimental outcomes show that the proposed strategy consistently outperforms the state-of-the-art in accuracy and robustness for segmenting images with fuzzy boundaries and intensity inhomogeneity. [ABSTRACT FROM AUTHOR]

[Display omitted] • We propose a new approach named NDO-NODE to stabilize the training and improve generalization of NODE, which injects the inductive bias of a function library on derivative calculation. • We prove the generalization ability of the learned NDO: it can output derivatives for functions belonging to the library with small errors. • Experiments show that NDO-NODE can consistently improve both the interpolation and extrapolation accuracy on these tasks with one pre-trained NDO. Also, it can stablize the training for stiff ODEs. Learning dynamics governed by differential equations is crucial for predicting and controlling the systems in science and engineering. Neural Ordinary Differential Equation (NODE), a deep learning model integrated with differential equations, is popular in learning dynamics recently due to its robustness to irregular samples and its flexibility to high-dimensional input. However, the training of NODE is sensitive to the precision of the numerical solver, which makes the convergence of NODE unstable, especially for ill-conditioned dynamical systems. In this paper, to reduce the reliance on the numerical solver, we propose to enhance the supervised signal in the training of NODE. Specifically, we pre-train a neural differential operator (NDO) to output an estimation of the derivatives to serve as an additional supervised signal. The NDO is pre-trained on a class of basis functions and learns the mapping between the trajectory samples of these functions to their derivatives. To leverage both the trajectory signal and the estimated derivatives from NDO, we propose an algorithm called NDO-NODE, in which the loss function contains two terms: the fitness on the true trajectory samples and the fitness on the estimated derivatives that are outputted by the pre-trained NDO. Experiments on various kinds of dynamics show that our proposed NDO-NODE can consistently improve the forecasting accuracy with one pre-trained NDO. Especially for the stiff ODEs, we observe that NDO-NODE can capture the transitions in the dynamics more accurately compared with other regularization methods. [ABSTRACT FROM AUTHOR]

The performance of existing underwater object detection methods severely degrades when they face the domain shift caused by complicated underwater environments. Due to the limited domain diversity in collected data, deep detectors easily memorize a few seen domains, which leads to low generalization ability. There are two common ideas to improve the domain generalization performance. First, it can be inferred that the detector trained on as many domains as possible is domain-invariant. Second, their hidden features should be equivalent because the images with the same semantic content are in different domains. This paper further excavates these two ideas and proposes a domain generalization framework that learns how to generalize across domains from Domain Mixup and Contrastive Learning (DMCL). First, based on the formation of underwater images, an image in one kind of underwater environment is the linear transformation of another underwater environment. Therefore, a style transfer model, which outputs a linear transformation matrix instead of the whole image, is proposed to transform images from one source domain to another, enriching the domain diversity of the training data. Second, the Mixup operation interpolates different domains on the feature level, sampling new domains on the domain manifold. Third, a contrastive loss is selectively applied to features from different domains to force the model to learn domain-invariant features but retain the discriminative capacity. With our method, detectors will be robust to domain shift. Also, a domain generalization benchmark S-UODAC2020 for detection is set up to measure the performance of our method. Comprehensive experiments on S-UODAC2020 and two object recognition benchmarks (PACS and VLCS) demonstrate that the proposed method is able to learn domain-invariant representations and outperforms other domain generalization methods. The code is available in https://github.com/mousecpn/DMC-Domain-Generalization-for-Underwater-Object-Detection.git [ABSTRACT FROM AUTHOR]

Recently, great progresses have been achieved under the support of memory mechanism when dealing with video object segmentation (VOS) problem. Despite its achievements, existing VOS approaches still suffer from abnormal samples, which derive from intrinsic video artifacts such as occlusion and motion blur. To mitigate the above issue, in this paper, we propose a quality-aware pattern diffusion (QPD) framework to boost the VOS performance. To achieve quality-aware pattern diffusion, a quality alignment mechanism is proposed, and it aims to promote the contributions of those normal samples while suppressing those abnormal ones during the feature propagation/diffusion processes. With our proposed quality alignment mechanism, the diffused instance features could be kept staying in the normal feature space, keeping from feature contamination caused by those low-quality samples. We first introduce a learnable quality evaluator to assess the sample qualities in both the temporal domain (i.e., across the historical frames), as well as the spatial domain (i.e., within the current frame). To achieve adaptive historical feature propagation into the current instance, a quality-aware long-term context propagation module is proposed, with which more stable instance representations could be achieved through the established quality-aware feature propagation process. A quality-aware pattern diffusion module is further introduced to address the spatial-domain abnormal samples, resulting in effective decoder feature refinement through building the quality-aware correspondence weights. Extensive experiments have demonstrated that our proposed quality alignment mechanism could boost the performance by a great margin over a strong baseline while achieving state-of-the-art performances on public VOS benchmarks. [ABSTRACT FROM AUTHOR]

To facilitate the deployment of convolutional neural networks on resource-limited devices, neural network pruning, especially filter pruning, has been shown to be a promising approach. Precise channel importance evaluation requires the extraction of global feature information. In this paper, we propose a novel filter pruning method, VNGEP, which combines intra- and inter-channel information to evaluate channel importance comprehensively. We describe the feature map correlation information from a graph perspective. The feature map tensor is converted into an undirected weighted graph, where the edge weights are the cosine distance between feature maps. To characterize the individual information of the feature maps, we present the feature map energy matrix and embed it into the above undirected weighted graph. Ultimately, the filter importance is measured by the von Neumann graph entropy, thus identifying filters that are less informative and more replaceable by other filters. Moreover, we systematically investigate the computational feasibility and data sensitivity of the proposed scheme. Pruning experimental results for several models on different datasets show the superiority of our approach. For example, with ResNet110, our method achieves a 48.3% and 52.1% reduction in model size and FLOPs, respectively, along with a 1.07% improvement in accuracy over the baseline model on CIFAR10. With ResNet50, we achieve an accuracy improvement of 0.25% over the baseline model on ImageNet, while the model size and FLOPs are reduced by 40.8% and 44.8%, respectively. [ABSTRACT FROM AUTHOR]

Clustering validation and identifying the optimal number of clusters are crucial in expert and intelligent systems. However, the commonly used cluster validity indices (CVI) are not relevant enough to measure data structures. They do not embed the necessary mechanisms to be as effective as that of the clustering algorithm used to give the clustering results. This paper proposes a novel CVI called PDBI (Partitioning Davies-Bouldin Index) initially inspired from the native idea of the Davies-Bouldin Index (DBI). PDBI is based on a strategy that consists in dividing each cluster into sub-clusters that redefine the concepts of internal homogeneity and cluster separation via the integration of sophisticated mechanisms. This strategy makes it possible to process a relevant CVI even in the case of complex data structures and in presence of clusters with noisy patterns. PDBI is deterministic, runs independently of a given clustering algorithm and generates a normalized score between 0 and 1. Numerous tests were carried out using 2-dimensional benchmark data sets and data generated in higher dimensions with consistent ground truths. The experimental comparisons with the state-of-the-art validity indices demonstrate the efficiency of the proposal in discovering the true number of clusters and dealing with various sorts of data sets. The PDBI demonstration as well as illustrations can be found on the author's website 1 1 A demonstration is available at: http://r-riad.net/ [ABSTRACT FROM AUTHOR]

The connection between humans and digital technologies has been documented extensively in the past decades but needs to be evaluated through the current global pandemic. Artificial Intelligence(AI), with its two strands, Machine Learning (ML) and Semantic Reasoning, has proven to be a great solution to provide efficient ways to prevent, diagnose and limit the spread of COVID-19. IoT solutions have been widely proposed for COVID-19 disease monitoring, infection geolocation, and social applications. In this paper, we investigate the usage of the three technologies for handling the COVID-19 pandemic. For this purpose, we surveyed the existing ML applications and algorithms proposed during the pandemic to detect COVID-19 disease using symptom factors and image processing. The survey includes existing approaches including semantic technologies and IoT systems for COVID-19. Based on the survey result, we classified the main challenges and the solutions that could solve them. The study proposes a conceptual framework for pandemic management and discusses challenges and trends for future research. [ABSTRACT FROM AUTHOR]

The adaptive event-triggered control of Markovian jump complex dynamic networks (MJCDN) with actuator faults is studied in this paper. A new adaptive fault-tolerant control method is introduced to prove that the synchronization error is asymptotically convergent. Compared with traditional event-triggered strategies, a more general adaptive event-triggered control scheme for MJCDN is proposed to reduce network traffic load more effectively. This paper not only considers the synchronization of MJCDN with actuator faults and time-varying delay but also studies the H ∞ disturbance attenuation performance of MJCDN with random disturbance and actuator faults under adaptive event-triggered controller with appropriate adaptive laws. The Zeno behavior is ruled out effectively in these two different situations. In the end, two simulation examples are provided to illustrate the validity and rationality of the proposed methods about the adaptive event-triggered control of MJCDN with actuator faults. [ABSTRACT FROM AUTHOR]

[Display omitted] • This paper addresses the problem of pedestrian trajectory prediction, which plays significant roles in many applications such as human-robot cooperation and video surveillance. • It proposes an evolving spatiotemporal graph attention network model, which employs a time-varying graph convolution to extract time-varying features and an evolving attention mechanism to describe the recursive temporal interactions. • It improves the pedestrian trajectory predicting results and proves the strength of the model with ablation studies. Predicting pedestrian trajectory is an essential task in many applications. While previous studies based on graphs seek to model spatiotemporal information among pedestrian interactions, most of them neglect the recursive and continuous relations between neighboring time points. In this paper, we propose an evolving spatiotemporal graph attention network to predict future trajectories of pedestrians. This model considers the evolving relations of social interactions between contiguous time points and uses coordinates. The interaction is modeled by an evolving and dynamic attention mechanism. The social influence of each pedestrians of current frame is evolved from that of last frame and will be utilized to generate the social influence of next frame. The proposed model was tested on two challenging datasets and the experimental results prove the strength of the model. [ABSTRACT FROM AUTHOR]

• A methodology to forecast time series with generalized neural networks is outlined. • A clever way of feature selection is proposed. • Strategies for dealing with time series with a trend are developed. This paper discusses how to forecast time series using generalized regression neural networks. The main goal is to take advantage of their inherent properties to generate fast, highly accurate forecasts. To this end, the key modeling decisions involved in forecasting with generalized regression neural networks are described. To deal with every modeling decision, several strategies are proposed. Each strategy is analyzed in terms of forecast accuracy and computational time. Apart from the modeling decisions, any successful time series forecasting methodology has to be able to capture the seasonal and trend patterns found in a time series. In this regard, some clever techniques to cope with these patterns are also suggested. The proposed methodology is able to forecast time series in an automatic way. Additionally, the paper introduces a publicly available R package that incorporates the best presented modeling approaches and transformations to forecast time series with generalized regression neural networks. [ABSTRACT FROM AUTHOR]

The advent of deep learning has brought great change to the community of computer science and also revitalized numerous fields where traditional machine learning methods failed to make breakthroughs. Benefitted from the development of deep learning, analysis of medical images, which used to be a challenging yet exhausting task carried out manually by physicians, has experienced fast development as well. However, training deep learning models in these systems for analysis from scratch can be quite challenging. The small-scale data can't guarantee the performance of the developed systems, while large-scale data is usually unavailable due to expensive costs in the process of collection and storage. To allow a fast transition from one domain to another for reuse, experts and researchers have extensively delved transfer learning, which turns out to be an efficient and low-cost learning technique. In this paper, we will present a comprehensive survey of transfer learning on medical image analysis. The imaging modalities include but not limits to Computed Tomography (CT), Ultrasound (US), and Magnetic Resonance Imaging (MRI). The subjects covered in this paper include the brain, breast, lung, kidney, etc. Besides, this survey provides systematic knowledge about deep learning and transfer learning for beginners. Readers with different backgrounds can easily catch up with the interdisciplinary knowledge and new trends of transfer learning via this survey. [ABSTRACT FROM AUTHOR]

Multi-objective immune algorithm (MOIA) is a heuristic algorithm based on artificial immune system model. Due to its characteristics of antibody clonal selection, automatic antigen recognition and immune memory in the immune system, artificial immune algorithm has become a research hotspot in the field of multi-objective optimization after the evolutionary algorithms. In this paper, most MOIAs can be classified into three main categories according to the type of problem solving, i.e., they are mostly designed to solve multi-objective optimization problems (MOPs), dynamic MOPs, and constrained MOPs. In this paper, a comprehensive survey is presented to summarize most existing MOIAs, in which their corresponding characteristics, principles and theoretical analyses are discussed in details. Moreover, the performance of MOIAs on solving various kinds of MOPs and many-objective optimization problems is also studied in our experimental comparisons. Finally, a brief conclusion is given to summarize the current drawbacks, challenges, and some future directions for MOIAs. [ABSTRACT FROM AUTHOR]

With the rapid development of society and the economy, autonomous driving techniques are widely applied in many areas, such as autonomous vehicles, autonomous drones, and robotics. As a dominating technique, deep learning has become more and more popular for 2-D and 3-D object detection. Numerous deep learning-based methods have been proposed to solve various vision issues. To further help with the development of unmanned systems, this paper presents a comprehensive survey of the recent processes from the past five years for 3-D object detection, road detection, traffic sign detection, and traffic light detection and classification. To summarize and analyze previous works in detail, this paper only focuses on deep learning-based object detection tasks in autonomous driving that take place when the input is a point cloud or image(s). It also presents comparative results for insight comparison and inspiring future researches. [ABSTRACT FROM AUTHOR]

Coronary artery disease is among one of the diseases human suffer most. Intravascular coronary arterial image analysis consists of denoising, segmentation, detection, and three-dimensional reconstruction, having a significant meaning for auxiliary diagnosis and treatment of coronary artery disease. Intravascular ultrasound (IVUS) and intravascular optical coherence tomography (IVOCT) are the two most commonly applied intravascular coronary arterial imaging techniques. Based on these fundamental imaging techniques, in recent years, many advanced technologies from traditional machine learning algorithms to deep learning methods were employed in the analysis of intravascular coronary arterial images and made huge progress in this field. In this survey, we reviewed more than one hundred papers published in top journals or conferences such as Neural Networks and MICCAI. These papers proposed approaches or schemes for the intravascular coronary arterial image analysis, including lumen border segmentation, atherosclerotic plaque characterization, media-adventitia segmentation, stent strut detection, and three-dimensional reconstruction. Our survey began with introducing coronary artery intravascular imaging techniques, essential neural networks, and deep learning and then presented an across-the-board review of methods, applications, and trends of intravascular image analysis. This survey is more comprehensive than other articles not only for its scope and reference number but also for discussing the future direction in this field. Compared to other review papers in this field, this article could assist beginners in constructing a basic knowledge frame of coronary artery intravascular image analysis methods and brought state-of-the-art progress in this field to fellow researchers. We hope this paper could benefit either the beginners for coronary arterial image analysis or experienced researchers. [ABSTRACT FROM AUTHOR]

Statistical techniques incorporated with machine-learning algorithms in unison with gene-environment interaction are giving unparalleled understanding of complex diseases. Accurate analysis and intricate capturing of common, rare, and low MAF (Minor Allele Frequency) variants alongside gene-environmental interaction is pivotal whilst concluding reliable and accurate classification of complex diseases. Various complex diseases including genres of diabetes Type 1 and Type 2 alongside the vastly under-researched Lada (Latent Autoimmune Diabetes in Adults) diabetes require further investigation alongside significant machine learning research to gain a deeper understanding of the disease complexities. Despite existing efforts, an ideal combination of statistical techniques with optimal machine-learning algorithms that can accurately capture and model the gene-environment interaction is lacking. Intentionally exploring future and simultaneously exploiting modern-day computational methods in genomic analysis, this paper profoundly investigates both the future and present interaction of statistical analysis techniques and machine-learning algorithms and Ensembles with gene-environmental factors. In this context, this paper firstly presents a conceptual understanding of genomic conventions; secondly, conducts potential future machine learning algorithms alongside an extensive analysis of a range of classification, regression and Ensemble techniques along with exhibiting their imperative relationship and roles in investigating and classifying common, rare variants and a wide array of gene-environmental factors; and thirdly, utilisation of statistical techniques in Genome Wide Association Studies is scrutinised whilst analysing common, rare and MAF variants. As an important contribution, this paper identifies efficient machine-learning algorithms alongside Ensemble models and future potential analysis techniques and exhibits their inherent characteristics that can enhance the reliability and accuracy of the gene-environment classification analysis. [ABSTRACT FROM AUTHOR]

In this paper, the gain-scheduled state estimation issue is investigated for a kind of complex networks subject to randomly occurring nonlinearities under bit-rate constraints. An array of random variables is introduced to govern the nonlinearities whose occurring probability is a time-varying but bounded value with known upper and lower bounds. A bit-rate constraint model is established and an encoding–decoding mechanism is proposed, under which an upper bound of the decoding error is acquired. The primary purpose of the issue considered in this paper is to design a gain-scheduled state estimator to obtain an estimate of the network state with an acceptable accuracy according to available output measurements. By means of the stochastic analysis and Lyapunov stability theory, a sufficient condition is provided such that the estimation error dynamics achieve the exponentially mean-square ultimate boundedness. The required estimator gain matrix is parameterized by solving a series of matrix inequalities. A numerical simulation is exploited to show the usefulness of the obtained gain-scheduled state estimator. [ABSTRACT FROM AUTHOR]

Time-variant Yang-Baxter-like matrix equation (YBLME) with the disturbances of noises is the hotspot in various scientific disciplines. The existing research, either can not handle the noise, or rely on the build-in numerical algorithm provided by MATLAB. Therefore, it is necessary to further study the digital-computer discrete solution of this problem. In this paper, the authors propose a noise-handling ten-instant discrete solution for the time-variant YBLME. By defining the matrix-form error function, Zhang neural network (ZNN) is exploited to design the continuous-time noise-handling ZNN model. For potential digital hardware (i.e., digital computer) realization, a discrete-time ZNN-based noise-handling ten-instant (DTZNH10i) algorithm, which is capable of handling three types of noises, is proposed on the basis of a Zhang time discretization (ZTD) formula. The convergence and precision of the proposed DTZNH10i algorithm are investigated and discussed. Theoretical analyses show the correctness and effectiveness of the proposed algorithm. The paper offers three examples of time-variant YBLME with disturbances of constant, linear, and bounded random noises to illustrate the efficacy and convergence of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Image recognition based on deep learning methods has gained remarkable achievements by feeding with abundant training data. Unfortunately, collecting a tremendous amount of annotated images is time-consuming and expensive, especially in grocery product recognition tasks. It is challenging to recognise grocery products accurately when the deep learning model is trained with insufficient data. This paper proposes multi-angle Generative Adversarial Networks (MAGAN), which can generate realistic training images with different angles for data augmentation. Mutual information is employed in the novel GAN to achieve the learning of angles in an unsupervised manner. This paper aims to create training images containing grocery products from different angles, thus improving grocery product recognition accuracy. We first enlarge the fruit dataset by using MAGAN and the state-of-the-art GAN variants. Then, we compare the top-1 accuracy results from CNN classifiers trained with different data augmentation methods. Finally, our experiments demonstrate that the MAGAN exceeds the existing GANs for grocery product recognition tasks, obtaining a significant increase in the accuracy. [ABSTRACT FROM AUTHOR]