The efficient utilization of computation and communication resources became a critical design issue in a wide range of networked systems due to the finite computation and processing capabilities of system components (e.g., sensor, controller) and shared network bandwidth. Event-triggered mechanisms (ETMs) are regarded as a major paradigm shift in resource-constrained applications compared to the classical time-triggered mechanisms, which allows a trade-off to be achieved between desired control/estimation performance and improved resource efficiency. In recent years, dynamic event-triggered mechanisms (DETMs) are emerging as a promising enabler to fulfill more resource-efficient and flexible design requirements. This paper provides a comprehensive review of the latest developments in dynamic event-triggered control and estimation for networked systems. Firstly, a unified event-triggered control and estimation framework is established, which empowers several fundamental issues associated with the construction and implementation of the desired ETM and controller/estimator to be systematically investigated. Secondly, the motivations of DETMs and their main features and benefits are outlined. Then, two typical classes of DETMs based on auxiliary dynamic variables (ADVs) and dynamic threshold parameters (DTPs) are elaborated. In addition, the main techniques of constructing ADVs and DTPs are classified, and their corresponding analysis and design methods are discussed. Furthermore, three application examples are provided to evaluate different ETMs and verify how and under what conditions DETMs are superior to their static and periodic counterparts. Finally, several challenging issues are envisioned to direct the future research.
This paper aims to propose a framework for manifold regularization (MR) based distributed semi-supervised learning (DSSL) using single layer feed-forward neural network (SLFNN). The proposed framework, denoted as DSSL-SLFNN is based on the SLFNN, MR framework, and distributed optimization strategy. Then, a series of algorithms are derived to solve DSSL problems. In DSSL problems, data consisting of labeled and unlabeled samples are distributed over a communication network, where each node has only access to its own data and can only communicate with its neighbors. In some scenarios, DSSL problems cannot be solved by centralized algorithms. According to the DSSL-SLFNN framework, each node over the communication network the initial parameters of the SLFNN with the same basis functions for semi-supervised learning (SSL). All nodes calculate the global optimal coefficients of the SLFNN by using distributed datasets and local updates. During the learning process, each node only exchanges local coefficients with its neighbors rather than raw data. It means that DSSL-SLFNN based algorithms work in a fully distributed fashion and are privacy preserving methods. Finally, several simulations are presented to show the efficiency of the proposed framework and the derived algorithms.
Many isolation approaches, such as zoning search, have been proposed to preserve the diversity in the decision space of multimodal multi-objective optimization (MMO). However, these approaches allocate the same computing resources for subspaces with different difficulties and evolution states. In order to solve this issue, this paper proposes a dynamic resource allocation strategy (DRAS) with reinforcement learning for multimodal multi-objective optimization problems (MMOPs). In DRAS, relative contribution and improvement are utilized to define the aptitude of subspaces, which can capture the potentials of subspaces accurately. Moreover, the reinforcement learning method is used to dynamically allocate computing resources for each subspace. In addition, the proposed DRAS is applied to zoning searches. The experimental results demonstrate that DRAS can effectively assist zoning search in finding more and better distributed equivalent Pareto optimal solutions in the decision space.
The digital camouflage spraying of special vehicles carried out by robots can greatly improve the spraying efficiency, spraying quality, and rapid adaptability to personalized patterns. The selection of spray tool and the accuracy of the adopted mathematical spray tool model has a great impact on the effectiveness of spray path planning and spraying quality. Since traditional conical spray tool models are not suitable for spraying rectangular digital camouflage, according to the characteristics of digital camouflage, the coating thickness cumulative distribution model of strip nozzle spray tool for 2D plane spraying and 3D surface spraying is derived, and its validity is verified by simulation. Based on the accumulation velocity model of the coating thickness on the curved surface (ASCT) and aiming at spraying path planning within the same surface and different surfaces, a path parameter optimization method based on coating uniformity evaluation of adjacent path overlapping area is proposed. Combined with the vehicle surface model, parameters such as path interval, spray tool angle and spray tool motion velocity can be calculated in real-time to ensure uniform coating. Based on the known local three-dimensional model of vehicle surface and the comprehensive spraying simulation, the validity of the purposed models: the coating thickness on the adjacent path area (APCT), the coating thickness on the intersection of two surfaces (CCCT), the coating thickness on the intersection of a plane and a surface (PSCT), and the optimization method of path parameters are verified. The results show that compared with the traditional spray tool, the strip nozzle can better ensure the uniformity of the coating thickness of digital camouflage spray. Finally, according to a practical spraying experiment, the results prove that the proposed models not only are effective but also meet the practical industrial requirements and are of great practical value.
Low-resolution face images can be found in many practical applications. For example, faces captured from surveillance videos are typically in small sizes. Existing face recognition deep networks, trained on high-resolution images, perform poorly in recognizing low-resolution faces. In this work, an improved multi-branch network is proposed by combining ResNet and feature super-resolution modules. ResNet is for recognizing high-resolution facial images and extracting features from both high- and low-resolution images. Feature super-resolution modules are inserted before the classifier of ResNet for low-resolution facial images. They are used to increase feature resolution. The proposed method is effective and simple. Experimental results show that the recognition accuracy for high-resolution face images is high, and the recognition accuracy for low-resolution face images is improved.
Working conditions of rolling bearings of wind turbine generators are complicated, and their vibration signals often show non-linear and non-stationary characteristics. In order to improve the efficiency of feature extraction of wind turbine rolling bearings and to strengthen the feature information, a new structural element and an adaptive algorithm based on the peak energy are proposed, which are combined with spectral correlation analysis to form a fault diagnosis algorithm for wind turbine rolling bearings. The proposed method firstly addresses the problem of impulsive signal omissions that are prone to occur in the process of fault feature extraction of traditional structural elements and proposes a “W” structural element to capture more characteristic information. Then, the proposed method selects the scale of multi-scale mathematical morphology, aiming at the problem of multi-scale mathematical morphology scale selection and structural element expansion law. An adaptive algorithm based on peak energy is proposed to carry out morphological scale selection and structural element expansion by improving the computing efficiency and enhancing the feature extraction effect. Finally, the proposed method performs spectral correlation analysis in the frequency domain for an unknown signal of the extracted feature and identifies the fault based on the correlation coefficient. The method is verified by numerical examples using experimental rig bearing data and actual wind field acquisition data and compared with traditional triangular and flat structural elements. The experimental results show that the new structural elements can more effectively extract the pulses in the signal and reduce noise interference, and the fault-diagnosis algorithm can accurately identify the fault category and improve the reliability of the results.
Retina vessel segmentation is a vital step in diagnosing ophthalmologic diseases. Traditionally, ophthalmologists segment retina vessels by hand, which is time-consuming and error-prone. Thus, more and more researchers are committed to the research of automatic segmentation algorithms. With the development of convolution neural networks (CNNs), many tasks can be solved by CNNs. In this paper, we propose an encoding-decoding network with a pyramid self-attention module (PSAM) to segment retinal vessels. The network follows a U shape structure, and it comprises stacked feature selection blocks (FSB) and a PSAM. The proposed FSB consists of two convolution blocks with the same weight and a channel-wise attention block. At the head of the network, we apply a PSAM consisting of three parallel self-attention modules to capture long-range dependence of different scales. Due to the power of PSAM and FSB, the performance of the network improves. We have evaluated our model on two public datasets: DRIVE and CHASE_DB1. The results show the performance of our model is better than other methods. The F1, Accuracy, and area under curve (AUC) are 82.21%/80.57%, 95.65%/97.02%, and 98.16%/98.46% on DRIVE and CHASE_DB1, respectively.
Fault Information Recognition for On-board Equipment of High-speed Railway Based on Multi-neural Network Collaboration
It is of great significance to guarantee the efficient statistics of high-speed railway on-board equipment fault information, which also improves the efficiency of fault analysis. Considering this background, this paper presents an empirical exploration of named entity recognition (NER) of on-board equipment fault information. Based on the historical fault records of on-board equipment, a fault information recognition model based on multi-neural network collaboration is proposed. First, considering Chinese recorded data characteristics, a method of constructing semantic features and additional features based on character granularity is proposed. Then, the two feature representations are concatenated and passed into the gated convolutional layer to extract the dependencies from multiple different subspaces and adjacent characters in parallel. Next, the local features are transmitted to the bidirectional long short-term memory (BiLSTM) to learn long-term dependency information. On top of BiLSTM, the sequential conditional random field (CRF) is used to jointly decode the optimized tag sequence of the whole sentence. The model is tested and compared with other representative baseline models. The results show that the proposed model not only considers the language characteristics of on-board fault records, but also has obvious advantages on the performance of fault information recognition.
An efficient convolution neural network (CNN) plays a crucial role in various visual tasks like object classification or detection, etc. The most common way to construct a CNN is stacking the same convolution block or complex connection. These approaches may be efficient but the parameter size and computation (Comp) have explosive growth. So we present a novel architecture called “DLA+”, which could obtain the feature from the different stages, and by the newly designed convolution block, could achieve better accuracy, while also dropping the computation six times compared to the baseline. We design some experiments about classification and object detection. On the CIFAR10 and VOC data-sets, we get better precision and faster speed than other architecture. The lightweight network even allows us to deploy to some low-performance device like drone, laptop, etc.
The problem of disguised voice recognition based on deep belief networks is studied. A hybrid feature extraction algorithm based on formants, Gammatone frequency cepstrum coefficients (GFCC) and their different coefficients is proposed to extract more discriminative speaker features from the original voice data. Using mixed features as the input of the model, a masquerade voice library is constructed. A masquerade voice recognition model based on a depth belief network is proposed. A dropout strategy is introduced to prevent overfitting, which effectively solves the problems of traditional Gaussian mixture models, such as insufficient modeling ability and low discrimination. Experimental results show that the proposed disguised voice recognition method can better fit the feature distribution, and significantly improve the classification effect and recognition rate.
The use of a lower sampling rate for designing a discrete-time state feedback-based controller fails to capture information of fast states in a two-time-scale system, while the use of a higher sampling rate increases the amount of computation considerably. Thus, the use of single-rate sampling for systems with slow and fast states has evident limitations. In this paper, multirate state feedback (MRSF) control for a linear time-invariant two-time-scale system is proposed. Here, multirate sampling refers to the sampling of slow and fast states at different sampling rates. Firstly, a block-triangular form of the original continuous two-time-scale system is constructed. Then, it is discretized with a smaller sampling period and feedback control is designed for the fast subsystem. Later, the system is block-diagonalized and equivalently represented into a system with a higher sampling period. Subsequently, feedback control is designed for the slow subsystem and overall MRSF control is derived. It is proved that the derived MRSF control stabilizes the full-order system. Being the transformed states of the original system, slow and fast states need to be estimated for the MRSF control realization. Hence, a sequential two-stage observer is formulated to estimate these states. Finally, the applicability of the design method is demonstrated with a numerical example and simulation results are compared with the single-rate sampling method. It is found that the proposed MRSF control and observer designs reduce computations without compromising closed-loop performance.