Remote sensing (RS) images change detection (CD) is essential for the surveillance and prevention of geohazards. Nevertheless, the current deep learning (DL)-based CD methods still face challenges such as pseudo changes, missed detections, and edge noise due to the inadequate research of temporal differences and inconsistent viewing angles between the dual-temporal images. In order to improve the perception of spatiotemporal variations and effectively manage complex motion in spatiotemporal data, this paper proposes a spatiotemporal multi-scale fusion and optical flow warping network (SMOW-Net). Initially, the internal fusion property of 3D convolution enables the simultaneous extraction and fusion of feature information in dual-temporal images. The spatiotemporal multi-scale feature encoder (SMFE) module is proposed to mitigate the semantic gap between low-level and high-level features. This module is designed to aggregate complementary feature information between each level through temporal and spatial independent processing and flexible temporal transposed convolutional layers. Furthermore, the optical flow warper (OFW) module is intended to improve the spatiotemporal dynamic modeling capability in order to manage complex motion data effectively, where a two-channel spatial deformation field is autonomously learned by the network to guide feature alignment. The performance advantage of our network over eleven state-of-the-art methods (SOTA) on the GVLM-CD, LEVIR-CD, WHU-CD, S2Looking, and LEVIR-CD+ datasets is validated by experimental results. Finally, we also introduce SMOW-Net-LW, a lightweight variant with significantly reduced model complexity, suitable for resource-constrained settings, while still achieving excellent performance. The code for this work is available at https://github.com/ChundeLiao/SMOW-Net .

Federated learning (FL) is well-suited for multimodal tasks due to its ability to protect privacy and support local training. However, the complexity of real-world sensor environments causes modality heterogeneity across clients. Some modalities may be missing altogether, making it difficult to construct a generalized global model. Existing multimodal federated learning methods often address modality-missing scenarios under simplified assumptions of modality heterogeneity, typically focusing on unimodal clients and modality-complete multimodal clients. Moreover, to mitigate performance degradation caused by missing modalities, some approaches assume the availability of auxiliary information at the server, which may be impractical in real-world scenarios. Therefore, we propose a novel heterogeneous multimodal Federated Learning with Mask-Restoration and Self-Guidance (FL-MRSG). The Mask-Restoration employs a masking strategy to simulate missing data during feature extraction, enabling the network to learn semantic features of missing modality. Furthermore, we introduce an innovative self-guidance mechanism that leverages the restored data as guidance information, enabling the network to distinguish between complete and missing data representations. In addition, we propose a personalized decoupled aggregation strategy to facilitate the collaborative training of a global model across heterogeneous modality clients. We extend the multimodal test set to arbitrary modality combinations to evaluate the robustness of the global model. Extensive experiments on MOSI and SIMS datasets demonstrate the effectiveness of the proposed FL-MRSG for arbitrary missing modalities.

It is well known that data drift may occur in complex industrial processes, which can cause changes in the distribution of data sampled by sensors. Therefore, the ability to generalize across unseen domains is essential for monitoring systems deployed in industrial processes. The invariant-complement domain generalization (ICDG) is proposed to alleviate data drift in industrial processes. This study reveals how the proposed covariant representation complements the invariant representation. Additionally, it derives novel theoretical error bounds characterizing the relationship between seen and unseen domains. Intuitively, the proposed invariant-complement representation method mitigates the influence of variant factors and encourages the learning of invariant and covariant representations. From the perspective of information theory, the boundaries for invariant and covariant representations are established and integrated as a joint learning objective with multiple information constraints. Theoretically, we elucidate that optimizing the ICDG objective function is equivalent to minimizing the upper bound of the empirical risk associated with unseen domains. This result helps ensure accurate prediction of quality variables under data drift. Case studies on the gas turbine (GT) dataset and the actual polyester esterification dataset validate the effectiveness of the proposed ICDG. The code is available athttps://github.com/heheding/ICDG

Federated learning (FL) enables collaborative training of deep learning models without requiring data to leave local clients, thereby preserving client privacy. The aggregation process on the server plays a critical role in the performance of the resulting FL model. The most commonly used aggregation method is weighted averaging based on the amount of data from each client, which is thought to reflect each client’s contribution. However, this method is prone to model bias, as dishonest clients might report inaccurate training data volumes to the server, which is hard to verify. To address this issue, we propose a novel secure Federated Data quantity-aware weighted averaging method (FedDua). It enables FL servers to accurately predict the amount of training data from each client based on their local model gradients uploaded. Furthermore, it can be seamlessly integrated into any FL algorithms that involve server-side model aggregation. Extensive experiments on three benchmarking datasets demonstrate that FedDua improves the global model performance by an average of 3.17% compared to four popular FL aggregation methods in the presence of inaccurate client data volume declarations.

Inspired by the immune-endocrine system, an improved biological comprehensive optimization algorithm (IBCOA) is proposed for industrial big data analysis and cloud manufacturing service matching. IBCOA employs a dual-level strategy: a bottom-level global optimization immune algorithm (GOIA) narrows down the search space to optimize short-term parameters, while a top-level fuzzy weighted comprehensive evaluation (FWCE) refines the solutions by incorporating long-term performance metrics. Experimental results demonstrate IBCOA’s superior performance, showing higher accuracy, recall, and F1 scores compared to least squares, decision trees, andK-means clustering, along with longer execution time and lower error rates. When tested on standard benchmarks including Iris (classification), MNIST (handwritten digits), and CIFAR-10 (image recognition), IBCOA achieves remarkable accuracies, highlighting its strong generalization and adaptability. The algorithm not only addresses immediate production requirements in polyester fiber industrial data analysis but also enhances long-term operational efficiency and product quality. By balancing stakeholder interests (suppliers, consumers, operators), it promotes sustainable development on industrial internet platforms. This work provides a robust solution for the industrial Internet of Things (IIoT) service evaluation and classification tasks, demonstrating transformative potential for cloud manufacturing resource allocation across diverse applications.

Different sampling rates are common for different variables in industrial processes because of the different electrical properties and requirements of sensors. Especially the sampling rate of quality variables is significantly lower than that of process variables. However, most soft sensors assume that industrial data is uniformly sampled, which differs significantly from actual industrial systems and may affect decision-making in the production process. An interpretable disentangled transfer learning (IDTL) quality prediction is proposed suitable for multirate industrial processes. First, a setness constructor is designed to diversify the original multirate data into multiple multirate sets to preserve information without data loss. Then, a disentangled transfer learning (TL) approach is proposed to infer domain-invariant and domain-specific representations from multiple multirate sets, thereby revealing the intrinsic properties of multirate industrial processes and improving the soft sensor performance. From the perspective of information theory, the theoretical representations for disentanglement and their connection to TL are established, laying a solid theoretical foundation for subsequent TL under complex working conditions. Our theoretical analysis shows that interpretable disentangled TL (IDTL) achieves optimal disentangled representations in equilibrium. Case studies of the debutanizer column dataset and the actual polyester esterification dataset validate the effectiveness of the proposed IDTL. Code is available at https://github.com/heheding/IDTL.

Imbalanced image classification faces critical challenges in balancing the quality and diversity of synthetic minority samples. This article proposes the improved estimation distribution algorithm-based latent feature distribution evolution (MEDA_LUDE) algorithm, an evolutionary algorithm-assisted deep distribution learning framework that optimizes latent feature distributions through a multivariate Gaussian mixture (GM) assumption and a novel four-phase training strategy. We introduce a large-margin GM (L-GM) loss to dynamically model covariances for feature learning and design a MEDA that evolves latent features via a similarity-guided fitness function, thus enhancing diversity while preserving synthesis quality. Extensive experiments demonstrate significant improvements: MEDA_LUDE achieves 95.9% accuracy on MNIST (imbalanced ratio-IR:100), surpassing state-of-the-art methods by 1.26% on CIFAR-10. For industrial fabric defect data sets, it elevates accuracy by 1.45% on DHU-FD and 0.92% on ALIYUN-FD, especially with precision and G-mean improvements of 2.5% and 1.17%, respectively, on DHU-FD. Visualizations confirm that MEDA_LUDE generates minority samples with superior quality-diversity tradeoffs. The framework's success in real-world fabric defect classification underscores its practical value in addressing imbalanced learning challenges.

The goal of relationship classification (RC) is to predict the semantic relationship between two entities in a given sentence. With the advent of deep learning and pretrained language models, RC research has progressed by leaps and bounds. However, the current studies are focused mainly on predicting semantic relationships from a predefined set. How to recognize unseen relationships remains a challenge, which is also known as the zero-shot RC (ZSRC) task. Some ZSRC-related methods directly map relationship categories to numerical indices, constraining the model's ability to autonomously infer and understand these relationships, while others rely heavily on manual definitions. To address these issues and inspired by the way of reasoning in which humans perform RC tasks, we propose a new framework to handle the ZSRC task through inference on category attributes (ICAs). The main idea of ICA is to detect the semantic relationship between promises, which are RC sentences, and hypotheses, which are relational sentences of entities created by templates. Specifically, instead of manual design, we introduce two hypothesis templates derived from the label words (LWs) and descriptions (LDs) associated with each relationship. These templates are used to automatically convert the RC data into the textual entailment (TE) format. Furthermore, they are fine-tuned with a pretrained TE model, facilitating the acquisition of relational knowledge and enabling the generalization of semantic reasoning rules learned from seen classes to unseen classes. Moreover, to implement multirelationship semantic inference for all unseen classes, we propose an entailment difference mechanism to enhance the reasoning capability of the model. Besides the current ZSRC test setting, we also examine our method in an even more challenging setting to deal with data scarcity in real-world applications. The outstanding performance of ICA on the FewRel and Wiki-ZSL datasets demonstrates its effectiveness in the ZSRC task.

The Dual Encoders (DE) framework maps image and text inputs into a coordinated representation space, and calculates their similarity directly. On the other hand, the Cross Attention (CA) framework performs modalities interactions after completing the feature embedding of images and text, and then outputs a similarity score. For scenarios with bulk query requests or large query sets, the latter is more accurate, but the former is faster. Therefore, this work finds a new way to improve the retrieval accuracy of the DE framework by borrowing the advantages of the CA framework. Drawing inspiration from image captioning, we introduce a text decoder in the model training stage to simulate the cross-modal interaction function, like the CA framework. The text decoder is eventually discarded, aligning our model with the DE framework. Finally, to ensure training stability and prevent overfitting, we modify the Self-Distillation from Last Mini-Batch and apply it to the retrieval areas. Extensive experiments conducted on the MSCOCO and Flickr30K datasets validate the effectiveness of our proposed methods. Notably, our model achieves competitive results compared to state-of-the-art approaches on the Flickr30K dataset.

Existing studies on relation extraction focus at the document level in a centralized training environment, requiring the collection of documents from various sources. However, this raises concerns about privacy protection, especially in sensitive domains such as finance and healthcare. For the first time, this work extends document-level relation extraction to a federated environment. The proposed federated framework, called FedLCC, is tailored for biomedical relation extraction that enables collaborative training without sharing raw medical texts. To fully exploit the models of all participating clients and improve the local training on individual clients, we propose a novel concept of localized context contrast on the basis of contrastive learning. By comparing and rectifying the similarity of localized context in documents between clients and the central server, the global model can better represent the documents on individual clients. Due to the lack of a widely accepted measure of non-IID text data, we introduce a novel non-IID scenario based on graph structural entropy. Experimental results on three document-level biomedical relation extraction datasets demonstrate the effectiveness of our method. Our code is available at https://github.com/xxxxyan/FedLCC.

Most fine-grained visual recognition methods endeavor to directly locate discriminative regions in intricate environments, but tend to overlook the object’s holistic structure, which may lead to misclassification due to overemphasizing incorrect areas. In this paper, we propose a coarse-to-fine paradigm, which prioritizes locating holistic structural regions of the target object, followed by a gradual search to locate discriminative areas. Specifically, we first design the “look into object” module to locate the areas encompassing the target’s holistic structure using prior information. Subsequently, without introducing additional parameters, we design a partial focus searching module to enhance feature representations of discriminative regions within the target’s structural composition. Ultimately, we segregate the foreground components from the original image, attaining a more precise characterization of the target. Furthermore, we demonstrate the practical application potential of our model in real-world industries through our self-constructed DHU-Fine-grained-6000 dataset. Comparative experiments on three public datasets indicate that the superiority of our approach over many recent methods and holds promising application potential in industrial production processes.

In recent years, neural architecture search (NAS) methods have been proposed for the automatic generation of task-oriented network architecture in image classification. However, the architectures obtained by existing NAS approaches are optimized only for classification performance and do not adapt to devices with limited computational resources. To address this challenge, we propose a neural network architecture search algorithm aiming to simultaneously improve the network performance and reduce the network complexity. The proposed framework automatically builds the network architecture at two stages: block-level search and network-level search. At the stage of block-level search, a gradient-based relaxation method is proposed, using an enhanced gradient to design high-performance and low-complexity blocks. At the stage of network-level search, an evolutionary multiobjective algorithm is utilized to complete the automatic design from blocks to the target network. The experimental results demonstrate that our method outperforms all evaluated hand-crafted networks in image classification, with an error rate of 3.18% on Canadian Institute for Advanced Research (CIFAR10) and an error rate of 19.16% on CIFAR100, both at network parameter size less than 1 M. Obviously, compared with other NAS methods, our method offers a tremendous reduction in designed network architecture parameters.

This article presents a robust variational Bayesian (VB) algorithm for identifying piecewise autoregressive exogenous (PWARX) systems with time-varying time-delays. To alleviate the adverse effects caused by outliers, the probability distribution of noise is taken to follow a t -distribution. Meanwhile, a solution strategy for more accurately classifying undecidable data points is proposed, and the hyperplanes used to split data are determined by a support vector machine (SVM). In addition, maximum-likelihood estimation (MLE) is adopted to re-estimate the unknown parameters through the classification results. The time-delay is regarded as a hidden variable and identified through the VB algorithm. The effectiveness of the proposed algorithm is illustrated by two simulation examples.

In this article, an approach for identification of an errors-in-variable system whose output is contaminated by heteroscedastic noise is developed. A Markov chain is applied to depict the correlation of the switching of heteroscedastic noise model. The estimation of model parameters adopts a variational Bayesian algorithm. The advantage of the Bayesian approach is the full probability description of the estimates while the classical expectation-maximization algorithm only provides point estimation. A simulated numerical example and an experimental study on a polyester fiber process are provided to demonstrate the effectiveness of the proposed method. Three performance indexes, normalized mean-absolute error, mean-relative error and root-mean-squared error, are used to evaluate the performance of the proposed algorithm. Meanwhile, Monte Carlo cross validations are performed to demonstrate the effectiveness and superiority of the proposed algorithm.

Relation classification (RC) task is one of fundamental tasks of information extraction, aiming to detect the relation information between entity pairs in unstructured natural language text and generate structured data in the form of entity-relation triple. Although distant supervision methods can effectively alleviate the problem of lack of training data in supervised learning, they also introduce noise into the data and still cannot fundamentally solve the long-tail distribution problem of the training instances. In order to enable the neural network to learn new knowledge through few instances such as humans, this work focuses on few-shot relation classification (FSRC), where a classifier should generalize to new classes that have not been seen in the training set, given only a number of samples for each class. To make full use of the existing information and get a better feature representation for each instance, we propose to encode each class prototype in an adaptive way from two aspects. First, based on the prototypical networks, we propose an adaptive mixture mechanism to add label words to the representation of the class prototype, which, to the best of our knowledge, is the first attempt to integrate the label information into features of the support samples of each class so as to get more interactive class prototypes. Second, to more reasonably measure the distances between samples of each category, we introduce a loss function for joint representation learning (JRL) to encode each support instance in an adaptive manner. Extensive experiments have been conducted on FewRel under different few-shot (FS) settings, and the results show that the proposed adaptive prototypical networks with label words and JRL has not only achieved significant improvements in accuracy but also increased the generalization ability of FSRC.

In multirobot patrolling problems, various dynamic situations require a higher level of cooperation among robots. The dynamic problems caused by moving objects are rarely studied yet. This work proposes a distributed event-driven cooperative strategy for multirobot systems to patrol moving objects autonomously. First, forward and backward utility functions are defined as criteria for robots to conduct two-way evaluation when they choose their targets to patrol. Then, three event types and a cooperative action considering energy consumption and visiting frequency comprehensively are proposed to improve coordination among robots during their execution processes. In simulation experiments, the proposed strategy shows significant advantages on decreasing the average and maximum unvisited time of moving objects compared with the state-of-the-art. A marine pollution monitoring case is simulated to demonstrate the practicability of this strategy.

Ureteral stent tubes are important medical devices used to repair ureteral obstruction or injury. However, relevant experiments of ureteral stent tubes are usually time-consuming and expensive. This research introduces a mechanical model that can simulate the force and deformation of ureteral stents. In addition, a novel optimization algorithm called improved exploration-enhanced gray wolf optimizer (IEE-GWO) is proposed to optimize parameters of the model. In order to balance exploration and exploitation of gray wolf optimizer (GWO), a dimension learning-based hunting (DLH) search strategy and a nonlinear control parameter strategy are integrated into the IEE-GWO. The experimental results show that the proposed IEE-GWO has better performance, such as fast convergence speed and high solution quality. Furthermore, the novel approach can improve the accuracy of the mechanical modal.

Most existing studies on computational modeling of neural plasticity have focused on synaptic plasticity. However, regulation of the internal weights in the reservoir based on synaptic plasticity often results in unstable learning dynamics. In this article, a structural synaptic plasticity learning rule is proposed to train the weights and add or remove neurons within the reservoir, which is shown to be able to alleviate the instability of the synaptic plasticity, and to contribute to increase the memory capacity of the network as well. Our experimental results also reveal that a few stronger connections may last for a longer period of time in a constantly changing network structure, and are relatively resistant to decay or disruptions in the learning process. These results are consistent with the evidence observed in biological systems. Finally, we show that an echo state network (ESN) using the proposed structural plasticity rule outperforms an ESN using synaptic plasticity and three state-of-the-art ESNs on four benchmark tasks.

Neural architecture search (NAS) provides an automatic solution in designing network architectures. Unfortunately, the direct search for complete task-dependent network architectures is laborious since training and evaluating complete neural architectures over a large search space are computationally prohibitive. Recently, one-shot NAS (OSNAS) has attracted great attention in the NAS community because it significantly speeds up the candidate architecture evaluation procedure through weight sharing. However, the full weight sharing training paradigm in OSNAS may result in strong interference across candidate architectures and mislead the architecture search. To alleviate the problem, we propose a partial weight sharing OSNAS framework that directly evolves complete neural network architectures. In particular, we suggest a novel node representation scheme that randomly activates a subset of nodes of the one-shot model in each generation to reduce the weight coupling in the one-shot model. During the evolutionary search, a tailored crossover operator randomly samples the nodes from two parent individuals or a single parent to construct new candidate architectures, thus effectively constraining the degree of weight sharing. Furthermore, we introduce a new mutation operator that replaces the chosen nodes of the one-shot model with randomly generated nodes to enhance the exploratory capability. Finally, we encode a set of pyramidal convolution operations in the search space, enabling the evolved neural networks to capture different levels of details in the images. The proposed method is examined and compared with 26 state-of-the-art algorithms on ten image classification tasks, including CIFAR series, CINIC10, ImageNet, and MedMNIST series. The experimental results demonstrate that the proposed method can computationally much more efficiently find neural architectures that achieve comparable classification accuracy to the state-of-the-art designs.

Data-driven soft sensors have been widely used in industrial processes for over two decades. Industrial processes often exhibit nonlinear and time-varying behavior due to complex physical and chemical mechanisms, feedback control, and dynamic noise. Lately, variational autoencoder (VAE) has arisen as one of the most prevalent methods for unsupervised learning of intricate distributions. Despite being successful in deep feature extraction and uncertain data modeling, it still suffers from instability and reconstruction error due to random sampling in the latent subspace representation of original input space. In this article, to deal with those limitations, constrained VAE (CVAE) is proposed by utilizing input sample information. Enthused by parallel interaction mechanism between the ventral and dorsal stream of the human brain in object recognition, parallel interaction spatial-temporal CVAE (PIST-CVAE) is proposed to extract spatial and temporal features from input samples. Lower dimensional nonlinear features extracted from PIST-CVAE are used to build the soft sensor. The effectiveness of CVAE and PIST-CVAE is demonstrated in an industrial case study, a polyester polymerization process. The obtained results demonstrate that CVAE is able to reconstruct inputs with higher accuracy and the proposed PIST-CVAE-based soft sensor yields more accurate estimations for the melt viscosity index of the polymerization process.

Moth-flame optimization algorithms are widely employed to solve optimization problems and achieve good performance. However, the algorithms suffer the shortcoming of prematurity because of the early gathering of flames. To solve this problem, the flame fusion mechanism is integrated to improve the exploratory behavior of the moth-flame optimization algorithm. The flame fusion mechanism provides a new way to evaluate the state of flame aggregation based on the distribution of flames and moths. When the concentration of flames is higher than the fusion threshold, the better flame will fuse other flames. And the fused flames will be regenerated to enhance the exploration behavior of the algorithm. At the same time, the fusion rate that determines the probability of flame fusion is introduced. The fusion rate changes during iteration to balance the exploration and exploitation behaviors of the algorithm. The improved moth-flame optimization is validated by ten benchmark functions. The results show that the optimization ability of the improved moth-flame optimization algorithm is improved, and the stability is higher than compared algorithms as well.

The performance of deep neural networks is heavily dependent on its architecture and various neural architecture search strategies have been developed for automated network architecture design. Recently, evolutionary neural architecture search (EvoNAS) has received increasing attention due to the attractive global optimization capability of evolutionary algorithms. However, EvoNAS suffers from extremely high computational costs because a large number of performance evaluations are usually required in evolutionary optimization, and training deep neural networks is itself computationally very expensive. To address this issue, this article proposes a computationally efficient framework for the evolutionary search of convolutional networks based on a directed acyclic graph, in which parents are randomly sampled and trained on each mini-batch of training data. In addition, a node inheritance strategy is adopted so that the fitness of all offspring individuals can be evaluated without training them. Finally, we encode a channel attention mechanism in the search space to enhance the feature processing capability of the evolved neural networks. We evaluate the proposed algorithm on the widely used datasets, in comparison with 30 state-of-the-art peer algorithms. Our experimental results show that the proposed algorithm is not only computationally much more efficient but also highly competitive in learning performance.

A service optimization method for polyester fiber production process is proposed. According to the production batch and production specifications, the method considers the service cost as the optimization objective, and uses data model to determine the specific process parameters in the polyester fiber production process. First, two options for the overall process of polyester fiber are introduced: on-demand manufacturing and product development. Second, the impact of different batch request tasks on the performance index of each stage is determined. Finally, the service optimization measures of different batches are proposed. By comparing the similarity between the current data samples and the overall data, the optimal production plan of the overall production process is formed. Simulation results show that the immune algorithm inspired from endocrine regulation has the best performance on the optimal decision-making combination, which is helpful for the development of new polyester products. We investigate how to reduce energy consumption of system resources, and how to choose the best service from a large number of candidate services. In the overall polyester fiber production process, users are not only consumers, but also designers and producers, achieving the real “integration of production and consumption”.

Echo State Network (ESN) is a fast and efficient recurrent neural network with a sparsely connected reservoir and a simple linear output layer, which has been widely used for real-world prediction problems. However, the capability of the ESN of handling complex nonlinear problems is limited by the relatively simple neuronal dynamics in the reservoir. Although the gated recurrent unit (GRU) model with multiple nonlinear operators has achieved an excellent performance, gradient-based training algorithms usually require intensive computational resources. In this paper, we present a novel ESN model based on GRUs to tackle complex real-world tasks while reducing the computational costs, taking advantage of the characteristics of both the ESN and the GRU models. In the proposed model, the reservoir unit is replaced by the sparsely connected GRU neurons. Experimental results on three regression problems demonstrate that the proposed method performs better than the original ESN and GRU models.

Relation extraction is an important task of information extraction. Most existing methods of Chinese language relation extraction are based on word input. They are highly dependent on the quality of word segmentation and suffer from the ambiguity of polysemic words. Therefore, a multi-feature fusion model is presented on the basis of character input, which integrates character-level features, word-level features and entity sense features into deep neural network models. Specifically, to alleviate the ambiguity of polysemy, the entity sense is introduced as external language knowledge to provide supplementary information for understanding the semantics of an entity in a given sentence. The Attention-Based Bidirectional Long Short-Term Memory Networks (Att-BLSTM) are proposed to capture features at the character level. To obtain more structural information, the convolutional layer (C-Att-BLSTM) is built upon the Att-BLSTM to capture features at the word level. Experiments are conducted on a public dataset of SanWen, and show that the proposed model achieves state-of-the-art results.

The intelligent devices in Internet of Things (IoT) not only provide services but also consider how to allocate heterogeneous resources and reduce resource consumption and service time as far as possible. This issue becomes crucial in the case of large-scale IoT environments. In order for the IoT service system to respond to multiple requests simultaneously and provide Pareto optimal decisions, we propose an immune-endocrine system inspired hierarchical coevolutionary multiobjective optimization algorithm (IE-HCMOA) in this paper. In IE-HCMOA, a multiobjective immune algorithm based on global ranking with vaccine is designed to choose superior antibodies. Meanwhile, we adopt clustering in top population to make the operations more directional and purposeful and realize self-adaptive searching. And we use the human forgetting memory mechanism to design two-level memory storage for the choice problem of solutions to achieve promising performance. In order to validate the practicability and effectiveness of IE-HCMOA, we apply it to the field of agricultural IoT service. The simulation results demonstrate that the proposed algorithm can obtain the best Pareto, the strongest exploration ability, and excellent performance than nondominated neighbor immune algorithms and NSGA-II.

Autoencoder (AE) is a deep neural network that has been widely utilized in process industry owing to its superior abilities of feature extraction and data reconstruction. Recently, assuming the latent variables to be random variables, a probabilistic variant of it called variational autoencoder (VAE) has achieved a major success in different applications. In this article, we develop two novel submodels based on deep VAEs (DVAE), which are further utilized to establish a soft sensor framework. By the use of our first submodel known as supervised DVAE (SDVAE), the distribution information of latent features can be obtained. This is used as a prior of the second submodel known as the modified unsupervised DVAE (MUDVAE). Then, a new soft sensor framework can be constructed by combing the encoder of SDVAE with the decoder of MUDVAE. Since our designed VAE has superior ability in data reconstruction, it also works well under the missing data situation which is common in process industries due to sensor failures. Thus, we extend the proposed soft sensor framework to handle the missing data situation. The effectiveness of our proposed soft sensor frameworks is finally demonstrated via an industrial polymerization dataset.

Multi-robot systems can be used to patrol a concerned part of ocean to ensure maritime safety under severe weather conditions. Seeking its optimal patrolling strategy to fulfill multi-optimization objectives is challenging. This paper presents a novel approach inspired by an immune-endocrine short feedback system to do so. Regulations produced by an endocrine system act on two phases of an artificial immune algorithm. First, a kind of hormone applied in a mutation process is proposed to decrease the number of undesirable solutions with the help of a Bayesian formula. Second, it is performed at a memory cell to suppress high-concentration antibodies and save high-quality individuals. To verify the feasibility of the proposed method, simulation experiments are conducted. The experimental results illustrate the desired effects of two regulation phases and the proposed method's performance in solving a maritime patrolling problem. Its high search ability and convergence speed are shown via its comparison with the other well-known algorithms.

Existing synaptic plasticity rules for optimizing the connections between neurons within the reservoir of echo state networks (ESNs) remain to be global in that the same type of plasticity rule with the same parameters is applied to all neurons. However, this is biologically implausible and practically inflexible for learning the structures in the input signals, thereby limiting the learning performance of ESNs. In this paper, we propose to use local plasticity rules that allow different neurons to use different types of plasticity rules and different parameters, which are achieved by optimizing the parameters of the local plasticity rules using the evolution strategy (ES) with covariance matrix adaptation (CMA-ES). We show that evolving neural plasticity will result in a synergistic learning of different plasticity rules, which plays an important role in improving the learning performance. Meanwhile, we show that the local plasticity rules can effectively alleviate synaptic interferences in learning the structure in sensory inputs. The proposed local plasticity rules are compared with a number of the state-of-the-art ESN models and the canonical ESN using a global plasticity rule on a set of widely used prediction and classification benchmark problems to demonstrate its competitive learning performance.

The search for multiple escaping targets is a significant issue of cooperative control in multi-agent systems since targets consciously seek to avoid being captured. Moreover, the assumption of continuous observations in existing works is not always suitable due to the limit of measuring equipment and uncertain movement of targets. Therefore, the problem with searching for escaping targets, which can be more aptly labeled "multiple escaping-targets search with random observation conditions" (MESROC), is difficult to address by conventional methods. Inspired by machine learning and the immune response mechanism of human bodies, a self-learning immune co-evolutionary network (SLICEN) is proposed. The SLICEN consists mainly of an immune cellular network (ICN) and an immune learning algorithm (ILA). The ICN provides feasible solutions to MESROC. Different kinds of network models are introduced to work as an ICN, such as convolutional neural networks, extreme learning machines, and support vector machines. The ILA evaluates the performance of feasible solutions and selects the optimal ones to further strengthen ICN reversely. Solutions are repeatedly improved through the co-evolution of ICN and ILA. An essential distinction to conventional machine learning approaches is that SLICEN works well without training samples. Simulations and comparisons demonstrate that patterns of advanced cooperative behavior among searchers function properly. SLICEN is an efficient method for solving MESROC.

Multiple solutions are often needed because of different kinds of uncertain failures in a plan execution process and scenarios for which precise mathematical models and constraints are difficult to obtain. This paper proposes an optimization strategy for multirobot task allocation (MRTA) problems and makes efforts on offering multiple solutions with same or similar quality for switching and selection. Since the mentioned problem can be regarded as a multimodal optimization one, this paper presents a niching immune-based optimization algorithm based on Softmax regression (sNIOA) to handle it. A prejudgment of population is done before entering an evaluation process to reduce the evaluation time and to avoid unnecessary computation. Furthermore, a guiding mutation (GM) operator inspired by the base pair in theory of gene mutation is introduced into sNIOA to strengthen its search ability. When a certain gene mutates, the others in the same gene group are more likely to mutate with a higher probability. Experimental results show the improvement of sNIOA on the aspect of accelerating computation speed with comparison to other heuristic algorithms. They also show the effectiveness of the proposed GM operator by comparing sNIOA with and without it. Two MRTA application cases are tested finally.

Existing multiobjective evolutionary algorithms (MOEAs) perform well on multiobjective optimization problems (MOPs) with regular Pareto fronts in which the Pareto optimal solutions distribute continuously over the objective space. When the Pareto front is discontinuous or degenerated, most existing algorithms cannot achieve good results. To remedy this issue, a clustering-based adaptive MOEA (CA-MOEA) is proposed in this paper for solving MOPs with irregular Pareto fronts. The main idea is to adaptively generate a set of cluster centers for guiding selection at each generation to maintain diversity and accelerate convergence. We investigate the performance of CA-MOEA on 18 widely used benchmark problems. Our results demonstrate the competitiveness of CA-MOEA for multiobjective optimization, especially for problems with irregular Pareto fronts. In addition, CA-MOEA is shown to perform well on the optimization of the stretching parameters in the carbon fiber formation process.

The ultimate goal of the Internet of Things (IoT) is to provide ubiquitous services. To achieve this goal, many challenges remain to be addressed. Inspired from the cooperative mechanisms between multiple systems in the human being, this paper proposes a bio-inspired self-learning coevolutionary algorithm (BSCA) for dynamic multiobjective optimization of IoT services to reduce energy consumption and service time. BSCA consists of three layers. The first layer is composed of multiple subpopulations evolving cooperatively to obtain diverse Pareto fronts. Based on the solutions obtained by the first layer, the second layer aims to further increase the diversity of solutions. The third layer refines the solutions found in the second layer by adopting an adaptive gradient refinement search strategy and a dynamic optimization method to cope with changing concurrent multiple service requests, thereby effectively improving the accuracy of solutions. Experiments on agricultural IoT services in the presence of dynamic requests under different distributions are performed based on two service-providing strategies, i.e., single service and collaborative service. The simulation results demonstrate that BSCA performs better than four existing algorithms on IoT services, in particular for high-dimensional problems.

Recently, deep learning has been widely applied in various areas and achieved remarkable research findings. The major reason that makes the deep learning paradigm successful is that it can effectively learn a hierarchical feature structure for the training data. However, most deep learning algorithms rely on massive well-labeled training datasets and hyper-parameter configurations. This paper proposed a novel methodology that uses the geometric characteristics of line-segment representations to optimize the hyper-parameters for the deep networks. The methodology is applied to a line-segment-based stacked auto-encoder to verify its effectiveness. It is found that the line-segment-based visualizations can increase the interpretability of the deep models and facilitate the configurations for the hyper-parameters.

Today, in the construction of smart city, the development of self-driving technology plays the key role. The explosion of convolutional neural network (CNN) technology has made it possible to utilize end-to-end tasks with images. However, today’s CNN has deeper, more accurate characteristics. If we do not improve the calculation method to reduce the number of network parameters, this feature makes it very difficult for us to run neural network computing in small devices. In this paper, we further optimize the network computing methods based on MobileNets to reduce number of network parameters. At the same time, in the network structure, we add BatchNormalization and Swish activation function. We designed our own network in the end-to-end prediction for steering angle in the self-driving car task. From the final simulation results, our neural network’s storage space can be reduced and the execution speed of neural network can be improved while maintaining the accuracy of the neural network.

In this paper, a computing speed improvement for the clonal selection algorithm (CSA) is proposed based on a degeneration recognizing (DR) method. The degeneration recognizing clonal selection algorithm (DR-CSA) is designed for solving complex engineering multimodal optimization problems. On each iteration of CSA, there is a large amount of eliminated solutions which are usually neglected. But these solutions do contain the knowledge of the nonoptimal area. By storing and utilizing these data, the DR-CSA is aimed to identify part of the new population as degenerated and eliminate them before the evaluation operation, so that a number of evaluation times can be avoided. This pre-elimination operation is able to save computing time because the evaluation is the main reason for the time cost in the complex engineering optimization problem. Experiments on both test function and a real-world engineering optimization problem (wet spinning coagulating process) are conducted. The results show that the proposed DR-CSA is as accurate as regular CSA and is effective in reducing a considerable amount of computing time.

In multi-camera video tracking, the tracking scene and tracking-target appearance can become complex, and current tracking methods use entirely different databases and evaluation criteria. Herein, for the first time to our knowledge, we present a universally applicable template library updating approach for multi-camera human tracking called multi-state self-learning template library updating (RS-TLU), which can be applied in different multi-camera tracking algorithms. In RS-TLU, self-learning divides tracking results into three states, namely steady state, gradually changing state, and suddenly changing state, by using the similarity of objects with historical templates and instantaneous templates because every state requires a different decision strategy. Subsequently, the tracking results for each state are judged and learned with motion and occlusion information. Finally, the correct template is chosen in the robust template library. We investigate the effectiveness of the proposed method using three databases and 42 test videos, and calculate the number of false positives, false matches, and missing tracking targets. Experimental results demonstrate that, in comparison with the state-of-the-art algorithms for 15 complex scenes, our RS-TLU approach effectively improves the number of correct target templates and reduces the number of similar templates and error templates in the template library.

Resubmission and replication are two fundamental and widely recognized techniques in distributed computing systems for fault tolerance. The resubmission based strategy has an advantage in resource utilization, while the replication based strategy can reduce the task completed time in the context of fault. However, few researches take these two techniques together for fault-tolerant workflow scheduling, especially in Cloud systems. In this paper, we present a novel fault-tolerant workflow scheduling (ICFWS) algorithm for Cloud systems by combining the aforementioned two strategies together to play their respective advantages for fault tolerance while trying to meet the soft deadline of workflow. First, it divides the soft deadline of workflow into multiple sub-deadlines for all tasks. Then, it selects a reasonable fault-tolerant strategy and reserves suitable resource for each task by taking the imbalance sub-deadlines among tasks and on-demand resource provisioning of Cloud systems into consideration. Finally, an online scheduling and reservation adjustment scheme is designed to select a suitable resource for the task with resubmission strategy and adjust the sub-deadlines as well as fault-tolerant strategies of some unexecuted tasks during the task execution process, respectively. The proposed algorithm is evaluated on both real-world and randomly generated workflows. The results demonstrate that the ICFWS outperforms some well-known approaches on corresponding metrics.

In this paper, a dynamic leader selection process of a multirobot system with leader-follower strategies is studied in terms of formation control. A fuzzy inference system is employed to evaluate the status of robots by means of their states. Based on the status, an affection-based model is proposed to trigger a leader selection module. Followers send out unsatisfied signals when they are disappointed at the current leader. The abashment value of the leader changes with its own status as well as the number of unsatisfied signals received from its followers. When its abashment value goes beyond a given threshold, a leader reselection process is triggered. Moreover, a swap-greedy algorithm is proposed to approximate the optimal solution for confirming the leader-follower relationship, which can be described as a combinatorial optimization problem to minimize the total travel distance of all the robots. Extensive simulation results demonstrate that the proposed model can improve the probability of a robot team escaping from local extreme points significantly, and even in the case of leader failure, the team can reselect a leader autonomously and keep moving toward the target.

In order to address the influence caused by unstable and uneven harvested energy among sensor nodes for clustering routing in energy harvesting wireless sensor networks (EH-WSNs), a novel clustering routing algorithm (CREW) is proposed in this work. The CREW is composed by cluster building phase and data transmission phase. In cluster building phase, the CREW uses two new concepts, Network Gradient and Waiting Time for cluster head Competition, to divide the network into unequal clusters and select the cluster heads based on residual energy and energy gain of nodes, respectively. In data transmission phase, it adopts an adaptive inter-cluster communication mechanism, to sufficiently store and utilize the harvesting energy. Finally, to verify the effectiveness of the proposed CREW, a series of experiments are conducted and compared with other related clustering routings for the EH-WSNs. Simulation results manifest that the CREW can provide effective clustering routing for the EH-WSNs and highlight the better performance of the proposed approach than that of similar techniques.

Since there is not a not a not a very very very suitable dynamical leader suitable dynamical leader suitable dynamical leader suitable dynamical leader suitable dynamical leader suitable dynamical leader suitable dynamical leader suitable dynamical leader suitable dynamical leader suitable dynamical leader selection model for selection model for selection model for selection model for selection model for selection model for selection model for selection model for formations control formations control formations control formations control formations control of the of the of the multi-robot system, we propose an affection-based dynamic leader selection strategy. A leader selection modular is used to switch the leader autonomously according to the cognized environmental statement based on two virtual affections, disappointment and abashment. The disappointment of followers will increase with the time spending in the awful scenario. When it exceeds a certain threshold, the followers will broadcast an unsatisfied signal. The abashment value of leader changes with the unsatisfied signals received from the followers and flutters with its own status at the same time. When the abashment value goes beyond the threshold, the leader re-selection process will be triggered. The abashment threshold is determined by the theoretic calculation. Plenty of simulation results show that the multi-robot system with dynamic leader-follower strategy has more probability of getting out of the woods, and also promote the survivability rate in the leader falling situation by re-selecting a leader autonomously.

A new global nonlinear predictor with a particle swarm-optimized interval support vector regression (PSO-ISVR) is proposed to address three issues (viz., kernel selection, model optimization, kernel method speed) encountered when applying SVR in the presence of large data sets. The novel prediction model can reduce the SVR computing overhead by dividing input space and adaptively selecting the optimized kernel functions to obtain optimal SVR parameter by PSO. To quantify the quality of the predictor, its generalization performance and execution speed are investigated based on statistical learning theory. In addition, experiments using synthetic data as well as the stock volume weighted average price are reported to demonstrate the effectiveness of the developed models. The experimental results show that the proposed PSO-ISVR predictor can improve the computational efficiency and the overall prediction accuracy compared with the results produced by the SVR and other regression methods. The proposed PSO-ISVR provides an important tool for nonlinear regression analysis of big data.

Most of the multivariable industrial production processes have latent failures on account of its complexity and uncertainty. This brings a great hidden threat to the control system's safety. Actuator fault is one of the commonest failures in control systems. This paper addresses a reconfigurable control system whose controller can be reconstructed when any actuator is faulty. Regard the control system as a biological immune system, an immune reconfigurable control system (IRCS) is designed. The IRCS includes an actuator monitor to imitate the immune surveillance mechanism, a decision module to imitate the immune response mechanism, a control strategy repository to imitate the immune memory mechanism and an adaptive learning module to imitate the immune learning mechanism. The IRCS is applied to the polyacrylonitrile carbon fiber coagulation bath, and the simulation results show that when there is any actuator fault, the IRCS can guarantee better performance compared with the conventional control schemes.

This paper studies on the predicted regression model of support vector machines (SVM). Aiming at the shortage that with the amount of samples grows, training time increases rapidly as well, we propose an optimization algorithm to optimize it for large scale dataset. The optimization algorithm is based on ensemble learning and dynamic clustering. Firstly, we use dynamic cluster method to generate different types of sub training set based on fuzzy granular. Then we construct SVM sub-learners. Afterwards we synthesize outputs of each sub-learner by using the strategy of mean squared error. Simulation experimental results demonstrate that the optimization algorithm can increase training speed obviously, and keep the original accuracy compared to traditional SVM.

A bidirectional optimizing approach for the melting spinning process based on an immune-enhanced neural network is proposed. The proposed bidirectional model can not only reveal the internal nonlinear relationship between the process configuration and the quality indices of the fibers as final product, but also provide a tool for engineers to develop new fiber products with expected quality specifications. A neural network is taken as the basis for the bidirectional model, and an immune component is introduced to enlarge the searching scope of the solution field so that the neural network has a larger possibility to find the appropriate and reasonable solution, and the error of prediction can therefore be eliminated. The proposed intelligent model can also help to determine what kind of process configuration should be made in order to produce satisfactory fiber products. To make the proposed model practical to the manufacturing, a software platform is developed. Simulation results show that the proposed model can eliminate the approximation error raised by the neural network-based optimizing model, which is due to the extension of focusing scope by the artificial immune mechanism. Meanwhile, the proposed model with the corresponding software can conduct optimization in two directions, namely, the process optimization and category development, and the corresponding results outperform those with an ordinary neural network-based intelligent model. It is also proved that the proposed model has the potential to act as a valuable tool from which the engineers and decision makers of the spinning process could benefit.

The stretching process is one of the key sections in fiber production, which is decisive to the quality of the final fiber products. Such a process raises high requirements on the control of the rollers with proper stretching ratios, and the large number of rollers with their special characteristics and the demand for synchronous running usually make the design of a good control scheme difficult. In this paper, a novel bioinspired multilayered intelligent cooperative controller (BMLICC) is proposed to provide a control plan for the interlinked rollers by organizing them into unified stretching units. Based on the multilayer regulation networks of neuroendocrine system in the human body, a networked controller structure is established. It consists of several components like rollers, distributed controllers, communication paths, and conversion units. The rollers in the same unit can exchange the working information rapidly to implement simultaneous response and cooperation. The stretching ratio can be kept stable and has strong resistance against the external disturbances on the stretching system. Both computer-simulation- and device-based experimental results demonstrate that the stretching unit with the proposed BMLICC can maintain its stretching ratio and effectively resist the external disturbances. This is beneficial to improve the performance of the stretched precursors and, furthermore, produce fibers with high quality. The proposed BMLICC can be easily extended to productions with multiple stretching units or industrial processes with similar mechanical structures for better control quality.

The topology control is a very important issue in wireless sensor networks (WSNs). Many approaches have been proposed to carry out in this aspect, including modern heuristic approach. In this paper, the Topology Control based on Artificial Immune Algorithm (ToCAIA) is proposed to solute the energy-aware topology control for WSNs. ToCAIA is a heuristic algorithm, which is heuristic from the immune system of human. In ToCAIA, the antibody is the solution of the problem, and the antigen is the problem. ToCAIA could be used to solve the multi-objective minimum energy network connectivity (MENC) problem, and get the approximate solution. The experiment result shows that the topology control by using ToCAIA can be utilized for WSNs network optimization purposes.

This paper introduces a new monocular stereo-vision sensor system which is suitable for visual servo control of parallel manipulator, consisting of one CCD camera and four pairs of symmetry mirrors, is designed for close quarters visual detection and motion control. The trinocular matching models is established from the geometric parameters, such as the angle between two face to face symmetric mirrors, angle and distance between two pairs of mirrors and the distance between CCD camera and mirrors. The trinocular Longuet-Higgins criteria has been introduced. The sensor performance and measuring accuracy are analyzed, which is necessary for the optimal design of the sensor. The binocular and trinocular search areas based on epipolar line theory are compared, it is proved that the search area is obviously decreased by using trinocular Longuet-Higgins criterion.