Electrolytic capacitors have unstable performance at the beginning of the test, which will have a huge impact on the steady operation of equipment that requires the installation or replacement of electrolytic capacitors. In this paper, a hybrid model based on the Autoregressive Integrated Moving Average (ARIMA) model, Bi-directional long short-term memory (Bi_LSTM), and Bayesian optimization (BO) is

Advances in machine learning technologies have led to increasingly powerful models in particular in the context of big data. Yet, many application scenarios demand for robustly interpretable models rather than optimum model accuracy; as an example, this is the case if potential biomarkers or causal factors should be discovered based on a set of given measurements. In this contribution, we focus on

Inspired by the phenomenon that the decoding weights of a well-trained autoencoder contain the information of the training samples, we proposed a data augmentation method by utilizing the decoding weights. Given a batch of training data, the autoencoder is trained and the decoding weights are activated; the decoding weights are then combined with the raw samples to generate augmented samples. Furthermore

Correlation Filter (CF) based algorithms play an important role in the field of Visual Object Tracking (VOT) due to its high performance and low computational complexity. While existing CF tracking algorithms suffer performance degradation due to inaccurate object modeling. In this paper, we improved the object modeling accuracy in both CF training stage and target detection procedure, and boosted

Graph generation with Machine Learning is an open problem with applications in various research fields. In this work, we propose to cast the generative process of a graph into a sequential one, relying on a node ordering procedure. We use this sequential process to design a novel generative model composed of two recurrent neural networks that learn to predict the edges of graphs: the first network

Deep-learning based image quality assessment (IQA) algorithms usually use the transfer learning method that transfers a pre-trained network for classification task to handle IQA task. Although it can overcome the problem of having insufficient IQA databases to some extent, it cannot distinguish between the important and unimportant deep features for the IQA task, which potentially leads to inaccurate

There is emerging interest in performing regression between distributions. In contrast to prediction on single instances, these machine learning methods can be useful for population-based studies or on problems that are inherently statistical in nature. The recently proposed distribution regression network (DRN) [13] has shown superior performance for the distribution-to-distribution regression task

This paper introduces a new procedure to train Minimal Learning Machines (MLM) for regression tasks. Besides that, we propose a new prediction process in MLM. A well-known drawback concerning the (original) MLM model formulation is the lack of sparseness. The most recent efforts on this problem strongly rely on the selection of reference points before training and prediction steps in MLM, all based

Sarcasm detection is a challenging natural language processing task for sentiment analysis. Existing deep learning based sarcasm detection models have not fully considered sentiment semantics, even though sentiment semantics is necessary to improve the performance of sarcasm detection. To deal with the problem, we propose a multi-level memory network using sentiment semantics to capture the features

In modern informatics society, human beings are becoming more and more attached to the computer. Therefore, understanding user behavior is critical to various application fields like sedentary analysis, human-computer interaction, and affective computing. Current sensor-based and vision-based user behavior understanding approaches are either contact or obtrusive to user s, jeopardizing their availability

Automatic architecture search is efficient to discover novel neural networks while it is mostly employed for pure vision or natural language tasks. However, cross-modality tasks are highly emphasized on the associative mechanisms between visual and language models rather than merely convolutional neural network (CNN) or recurrent neural network (RNN) with the best performance. In this work, the intermediary

Point clouds, as a kind of 3D objects representation, are the most primitive outputs obtained by 3D sensors. Unlike 2D images, point clouds are disordered and unstructured. Hence the classification techniques such as the convolution neural network are not applicable to point cloud analysis directly. To solve this problem, we propose a novel network to extract point clouds feature, named attention-based

In this work, output-feedback control problems for a class of discrete-time non-affine nonlinear systems with unknown control directions and input constraints are considered by using reinforcement learning (RL) method. Two neural networks (NNs) implement the control: 1) a critic NN that estimates a non-quadratic strategic utility function (SUF) and 2) an action NN that generates optimized control input

Image attribute editing is a challenging problem that has been recently studied by many researchers using generative networks. The challenge is in the manipulation of selected attributes of images while preserving the other details. The method to achieve this goal is to find an accurate latent vector representation of an image and a direction corresponding to the attribute. Almost all the works in

User-generated product reviews contain a lot of valuable information including users’ opinions on products and product features that is not fully exploited by the current recommendation models. Similarly, the metadata information related to the products, about the reviews and about the users who have written the reviews has rarely been exploited for recommender systems. These heterogeneous information

The amount of real-time communication between agents in an information system has increased rapidly since the beginning of the decade. This is because the use of these systems, e.g. social media, has become commonplace in today’s society. This requires analytical algorithms to learn and predict this stream of information in real-time. The nature of these systems is non-static and can be explained,

In this paper, a method of Active Disturbance Rejection Controller (ADRC) is proposed based on Q-learning of Reinforcement Learning (RL) for multi-area interconnected power system. Excessive changes in load can cause instability to the system. Therefore, the ADRC controller is used to keep the load within rated range for its strong anti-interference performance and Q-learning algorithm to select the

Abnormal electricity consumption (AEC) caused huge economic losses to power supply enterprises in the past years, and also posed severe threats to the safety of peoples’ daily live. An accurate AEC detection is crucial to reducing the non-technical losses (NTLs) suffered by power supply enterprises and the State Grid. Comparing with the huge amount of electricity data flow, AEC data are relative few

This paper presents an adaptive neuro-fuzzy PID controller based on twin delayed deep deterministic policy gradient (TD3) algorithm for nonlinear systems. In this approach, the observation of the environment is embedded with information of a multiple input single output (MISO) fuzzy inference system (FIS) and have a specially defined fuzzy PID controller in neural network (NN) formation acting as the

In recent years, convolution neural networks (CNN) have achieved substantial advantages for single image super resolution (SISR). However, as the depth and width of the networks increase, the model parameters and computation become more complicated. To solve these problems, we propose a lightweight network structure for super-resolution which adopts the multi-view information fusion strategy. The proposed

In recent years, single image super-resolution (SR) methods based on deep convolutional neural networks (CNNs) have made significant progress. However, due to the non-adaptive nature of the convolution operation, they cannot adapt to various characteristics of images, which limits their representational capability and, consequently, results in unnecessarily large model sizes. To address this issue

Many-core neural network chip is widely developed and used for both the deep learning and neuromorphic computing applications. Many-core architecture brings high parallelism while makes the model-to-core mapping intractable. In order to decrease the routing time, transmission packets amount and energy consumption, along with deadlock-free performance for inter-core data movement, we formulate an optimization

In this paper, we propose an attention-guided dual spatial-temporal non-local network for video super-resolution (ADNLVSR). We integrate temporal and spatial non-local self-similar contexts from continuous video frames after motion compensation, and merge the features of different levels discriminatively with channel attention mechanism for target frame. During motion compensation, unlike previous

Face stands out as a preferable biometric trait for automatic human authentication as it is intuitive and non-intrusive. This paper investigates various feature-based automatic face recognition approaches in detail. High degree of freedom in head movement and human emotion leads a face recognition system to face critical challenges in terms of pose, illumination and expression. Human face also undergoes

Hashing methods have been widely applied to approximate nearest neighbor search in large-scale image retrieval due to its fast search speed and efficient storage space. In practice, most images are with multiple category-aware objects, i.e., multi-label images. This paper focuses on hash code learning for multi-label image retrieval. Most existing hashing methods directly extract one patch such as

In the BCI rehabilitation system, the decoding of motor imagery tasks (MI-tasks) with dipoles in the source domain has gradually become a new research focus. For complex multiclass MI-tasks, the number of activated dipoles is large, and the activation area, activation time and intensity are also different for different subjects. The means by which to identify fewer subject-based dipoles is very important

With the rapid growth of wind power penetration into modern power grids, wind speed forecasting (WSF) becomes an increasing important task in the planning and operation of electric power and energy systems. However, WSF is quite challengeable due to its highly varying and complex features. In this paper, a novel hybrid deep neural network forecasting method is constituted. A feature selection method

Quality of life (QoL) is an effective index of well-being, including physical health, aspect of social activity, and mental state of individuals. A new approach that uses a deep-learning architecture to estimate the score of a user's QoL is presented. This system was built using a combination of a 3D convolutional neural network and a support vector machine for multimodal data. In order to evaluate

In this paper, a novel image-based visual servoing (IBVS) method using Extreme Learning Machine (ELM) and Q-learning is proposed to solve the problems of complex modeling and selection of the servo gain. First, the pseudoinverse of the interaction matrix is approached by ELM which avoids the singularity of the interaction matrix effectively and is robust to interferences such as feature noises and

The condition monitoring of concrete surface plays a significant role in civil infrastructure management system. Crack is the main threat to concrete surface of buildings, bridges, roads and pavements. This issue has been researched for several decades, however, it is still a challenge to classify crack since there are many inferior factors, e.g., intense inhomogeneity, structure complexity and background

Channel pruning is one of the important methods for deep model compression. Most of existing pruning methods mainly focus on classification. Few of them conduct systematic research on object detection. However, object detection is different from classification, which requires not only semantic information but also localization information. In this paper, based on discrimination-aware channel pruning

In this paper, adaptive general type-2 fuzzy neural network control for motion balance adjusting of a power-line inspection robot is developed. It is used to enhance the anti-interference ability of the controlled plant. General type-2 fuzzy system is adopted because of its ability to more effectively handle uncertainties which may exist as external disturbances and parameter perturbations. The structure

In this paper an effective graph learning method is proposed for clustering based on adaptive graph regularizations. Many graph learning methods focus on optimizing a global constraint on sparsity, low-rankness or weighted pair-wise distances, but they often fail to consider local connectivities. We demonstrate the importance of locality by generalizing the Locality-constrained Linear Coding (LLC)

Brain-machine interface (BMI) is a useful technology which creates a new way for disable people to communicate with the world, but experimenting with human brains is risky. Hence, a precise mathematical model of the information transmission in the process of limb movement is necessary to be established. In this paper, firstly, we improve the classical single-joint information transmission (SJIT) model

Parkinson’s disease is a progressive neurodegenerative disorder often accompanied by impairment in articulation, phonation, prosody and fluency of speech. In fact, speech impairment is one of the earliest Parkinson’s disease symptoms, and may be used for early diagnosis. We present an experimental study of identification of Parkinson’s disease and assessment of disease progress from speech using Gaussian

Effective person re-identification (Re-ID) is often required in real applications. While most exiting approaches either assume the detected pedestrian bounding box well-aligned or utilize limited human structural information (pose, attention, segmentation) to calibrate the misalignment. However, the value of utilizing attributes for pedestrian alignment is still under explored. Furthermore, the hierarchy

In this paper, we proposed a sparse semantic map building method and an outdoor relocalization strategy based on this map. Most existing semantic mapping approaches focus on improving semantic understanding of single frames and retain a large amount of environmental data. Instead, we don't want to locate the UGV precisely, but use the imprecise environmental information to determine the general position

A generalization of real-, complex-, and quaternion-valued neural networks is represented by matrix-valued neural networks (MVNNs), for which the states and weights are matrices. The dissipativity of impulsive MVNNs with leakage delay and mixed delays is studied in this paper, by giving sufficient criteria expressed in terms of real-valued linear matrix inequalities. After decomposing the MVNNs into

Multi-view clustering has received an increasing attention in many applications, where different views of objects can provide complementary information to each other. Existing approaches on multi-view clustering mainly focus on extending Non-negative Matrix Factorization (NMF) by enforcing the constraint over the coefficient matrices from different views in order to preserve their consensus. In this

Activation functions play important roles in determining the depth and non-linearity of deep learning models. Since the Rectified Linear Unit (ReLU) was introduced, many modifications, in which noise is intentionally injected, have been proposed to avoid overfitting. Exponential Linear Unit (ELU) and their variants, with trainable parameters, have been proposed to reduce the bias shift effects which

Learning paradigms that use random basis functions provide effective tools to deal with large datasets, as they combine efficient training algorithms with remarkable generalization performances. The paper first considers the affinity between the paradigm of learning with similarity functions and the Extreme Learning Machine (ELM) model, and reformulates the mapping scheme of ELMs. A mapping scheme

Human scanpath represents the sequence of human eye fixations, revealing the dynamic process of saccadic eye movement when a natural scene is freely viewed by humans. It is valuable to have an in-depth understanding of the dynamic visual attention and visual search behavior. In this paper, a deep convolutional saccadic model (DCSM) is proposed to predict human scanpath. The model simultaneously predicts

In this paper, we first established the fractional order memristive multidirectional associative memory neural networks (FMMAMNNs) model, and then considered its fixed-time synchronization control problem. On the basis of sliding model control and Lyapunov stability theorem, a fractional order sliding mode controller is constructed. By adding this controller to the response system, the error of the

In this paper, the H∞ control problem is investigated for a time-delayed two-dimensional (2-D) network under the random access protocol (RAP). The control input is transmitted to the actuator via a network with communication constraint, where only one signal obtains the network access at each transmission instant, and the RAP is adopted here to schedule the data transmission which is depicted by an

At present, the traditional islanded microgrid is changing to a cyber-physical system. And the data in its cyber layer is often used to solve practical problems in the physical layer through sensors and communicators. But the use of communication data also brings a lot of problems. Among them, the upload interruption problem (i.e., communicator or sensor failure) will make a heavy impact on the system

In order to monitor the roller states online running on the belt conveyor, one class of fault diagnosis systems based on audio is studied in this paper. Firstly, the audio data is collected from the belt conveyor by sensors, which is analyzed using the stacked sparse encoders and convolutional neural network. Secondly, the fault features are extracted from the audio data by using spectral clustering

Point cloud based 3D objection plays a crucial role in real-world applications, such as autonomous driving. In this paper, we propose the Multi-view Semantic Learning Network (MVSLN) for 3D object detection, an approach considering the feature discrimination for LIDAR point cloud. Since the discrete and disordered nature of point cloud, most existing methods ignore the low-level information and focus

In this paper, we address the issue of optimal bidding strategy selection for Electric Vehicles (EVs) charging in an auction market. The problem of EV charging has attracted growing attention as EVs become more and more popular. We consider the scenario that EV owners submit their bids for charging to the charging station, and then charging station determines the winning EVs who are admitted to charge

The ever increasing proportion of photovoltaic (PV), which is, in effect, a random and intermittent energy source, makes PV power forecasting increasingly important for power grid stability. Artificial neural networks (ANN) have become one of the commonly utilized methods in PV power prediction. Since there is no ideal theoretical guidance as yet on the determination of the number of hidden layers

Solar power is an important renewable energy resource and acts as a major contributor to replacing fossil fuel generators and reducing carbon emissions. However, the intermittent power output due to the uncertain solar irradiance significantly challenges the economic integrations of solar generation within the existing power system, which calls for effective forecasting methods to improve the solar

At present, most Chinese text summarization algorithms use the sequence-to-sequence model, but this model is prone to the problems of unknown words and incomplete content generation. To address these problems, we propose a new two-stage automatic text summarization method using keyword information and adversarial learning in this paper. On the one hand, the proposed method integrates the keyword information

In this paper, an observer-based adaptive neural network finite-time dynamic surface control method is proposed for the position tracking control of PMSM stochastic nonlinear systems with iron losses. First, the finite-time technology is used to realize the fast and effective tracking of the desired signal and make the system have better robust performance. Then, the adaptive neural network (NN) technology

LSTM network is an effective RNN model to predict the system RUL for its superior performance in sequential data processing. Usually, networks trained by life-cycle labeled dataset would possess similar RUL predicting accuracies, because the network training algorithm could ensure the network optimality for the whole training dataset. However, for networks trained by non-life-cycle labeled samples

In this paper, we consider a four-neuron bi-directional associative memory (BAM, for short) neural network with two delays. We choose connection weights and the sum of delays as bifurcation parameters and derive the critical values where a double Hopf bifurcation may occur by analyzing the associated characteristic equation which is a fourth-degree polynomial exponential equation. Meanwhile, we obtain

Due to technological advances, machines are increasingly present in people’s daily lives. Thus, there has been more and more effort to develop interfaces that provide an intuitive way of interaction, such as dynamic gestures. Currently, the most common trend is to use multimodal data, as depth and skeleton information, to enable dynamic gesture recognition. However, it would be more interesting if

Pedestrian detection in a crowd is a challenging task because of intra-class occlusion. More prior information is needed for the detector to be robust against it. Human head area is naturally a strong cue because of its stable appearance, visibility and relative location to body. Inspired by it, we adopt an extra branch to conduct semantic head detection in parallel with traditional body branch. Instead

Neural architecture search automates the design of deep neural network, and thus saves the costly manpower in applications like wildlife identification. However, the search may consume a lot of time to find the ideal architecture due to the bottleneck like estimating architecture performance. To reduce time cost, a novel method based on reinforcement learning is proposed in this paper. The proposed

In this paper, we are concerned with the finite-/fixed-time synchronization(FFTS) problem of delayed reaction-diffusion recurrent neural networks (RNNs) with discontinuous activations. By designing a novel unified controller, with the help of theory of Filippov regularization, and a generalized finite-/fixed-time convergence theorem, we establish a threshold FFTS dynamics, which is determined by the