Facial Expression Recognition(FER) is a key task in the broader landscape of affective computing and human-computer interaction, enabling machines to interpret human emotions. To better learn discriminative features under complex facial variations, recent FER research has increasingly adopted multi-branch fusion architectures that aim to capture complementary features from diverse perspectives. However, existing multi-branch fusion strategies, including static weighting, simple concatenation, or uncertainty-aware modeling, lack the capacity to comprehensively capture and reconcile the reliability variations across both individual instances and structural branches. To overcome these limitations, we propose a novel multi-branch fusion strategy, named Dual Uncertainty-Aware Fusion Framework(DUAFF), which improves the discriminability of integrated features by simultaneously modeling instance-wise uncertainty and inter-branch correlations. Specifically, the proposed method comprises two complementary modules: Instance-Discrepant Uncertainty-Aware Fusion Module (ID-UAFM) and Branch-Discrepant Uncertainty-Aware Fusion Module (BD-UAFM). ID-UAFM is introduced to perform channel-wise entropy analysis between semantically distinct samples to estimate instance-level uncertainty, enabling selective channel-wise fusion that emphasizes reliable representations while suppressing uncertain responses. BD-UAFM is further proposed to capture structural uncertainty by evaluating the relative reliability of features across multiple branches and adaptively weighting their contributions based on inter-branch discrepancies. Experimental results demonstrate that the proposed DUAFF consistently outperforms POSTER across three benchmark datasets, achieving accuracy improvements of 0.23 % on RAF-DB, 0.69 % on FER2013, and 0.29 % on AffectNet (7-class), thereby confirming its effectiveness in enhancing the reliability and discriminability of facial representations.

Compressive strength is the critical quality metric in industrial cement production, yet conventional assessment relies on destructive 28-day tests or inaccurate accelerated methods, hindering timely quality control. These methods inherently causesample scarcity(only 52–195 batches/year/plant) due to the 28-day curing requirement, labor-intensive specimen preparation, and destructive testing protocols—rendering them insufficient for data-driven models requiring large samples. Concurrently, plants facepartial observabilitywith arbitrary critical features (e.g., chemical composition) missing due to sensor limitations and prohibitive assay costs. While machine learning models accelerate prediction, their deterministic single-value outputs fail to infer missing features under partial observability and require extensive samples unattainable under scarcity, causing significant compliance risks and overdesign costs. We resolve these by reframing strength prediction as a probability density estimation task, replacing single-value estimates with full probability densities. Our proposed cement strength density estimator (CSDE): first, outputs strength as Gaussian mixture densities,second, resolves partial observabilityvia latent variable inference, andthird, overcomes sample scarcitythrough likelihood optimization. Validated on industrial data under partial observability and scarcity, CSDE exhibits only 2.78% MAE degradation under 82% feature masking (versus 3.73% for MLPs) and achieves 97% of strengths within 95% confidence intervals. By converting densities into compliance metrics [P(strength$\geq$critical value)], CSDE flags high-risk batches, reduces overdesign costs, and supports timely quality interventions. The framework is extensible to flexural/tensile strength prediction via input redefinition.

Speech-driven 3D facial animation aims to generate natural and expressive facial movements from speech. Although significant progress has been made, existing methods still face challenges in generating realistic upper facial expressions. Specifically, existing methods that jointly optimize the holistic face tend to overlook fine-grained spatial movements due to motion differences across facial regions. Pre-trained speech feature extractors, which emphasize long-term dependencies, provide limited fine-grained temporal cues. In this work, we propose a novel framework, EETalk, to enhance the realism of facial expressions, which captures fine-grained spatial information and f ine-grained temporal dynamics from speech. To alleviate loss of fine-grained spatial information, we propose a novel disassemble and-reassemble modeling strategy. This strategy constructs two independent motion representation spaces for the upper and lower faces, allowing for the capture of weak upper-face movements while preserving motion diversity. Then, we propose a Cross-Region Coordination Module to ensure the synchronization and coordination of the movements from the independent upper and lower faces. To effectively capture facial micro-expressions, we incorporate fine-grained time-varying features to compensate for the short-timescale details underrepresented in the long term semantic features extracted by pre-trained self-supervised models, thereby improving the generation of fast, subtle facial expressions. Experimental results demonstrate that our approach significantly improves motion accuracy, expression consistency, and perceptual quality compared to existing methods.

Facial Expression Recognition (FER) has recently plays a crucial role in advancing human-computer interaction systems, aiming to understand users' inner states and underlying intentions. However, FER in real-world scenarios remains challenging due to significant label noise, caused by ambiguous facial expressions in low-quality images and annotation bias. To tackle this issue, this paper proposes a novel framework, Pseudo-Entropy Guided Complementary Learning (PEGCL), designed to robustly handle noisy labels by leveraging complementary information, which trains networks using all complementary labels defined as “facial expression images that do not belong to complementary emotion labels.” This approach effectively utilizes non-target emotion labels to mitigate the impact of label noise, rather than relying solely on annotated emotion labels. Specifically, the proposed PEGCL framework consists of three components: logit normalization to stabilize predicted probabilities and prevent gradient explosions, transformed complementary learning to redistribute the optimization focus across complementary categories by leveraging pseudo-entropy guided, and random complementary label dropping to dynamically exclude subsets of complementary labels, enhancing generalization and preventing overfitting. These components collectively ensure robust and efficient optimization under noisy label conditions. Importantly, the proposed PEGCL does not require explicit noise estimation or complex label correction mechanisms, making it a simple and effective solution for real-world FER tasks. Extensive experiments on benchmark FER datasets demonstrate that PEGCL consistently outperforms existing methods, achieving the state-of-the-art robustness against label noise while maintaining high classification accuracy.

The autoencoder (AE) is an efficient feature extraction tool that learns latent representations from raw data by minimizing the reconstruction loss. Building upon the AE architecture, deep clustering models are designed to jointly optimize the deep neural network and perform unsupervised clustering. However, existing methods directly impose the clustering objective on the latent features produced by the AE network, thereby neglecting the potential conflict between data clustering and data representation. Specifically, data clustering aims to enhance data aggregation, whereas data representation focuses on ensuring that latent features faithfully reflect the manifold structure of the raw data. To address this issue, this article proposes an innovative expanded deep embedding clustering (E-DEC) model, in which the AE network is employed to seek better latent representations, and a novel residual expansion module (REM) is integrated to construct an expanded feature space that better serves clustering tasks. Furthermore, adversarial learning between the soft cluster assignments and a prior one-hot distribution is adopted in lieu of the conventional Kullback–Leibler (KL) divergence, so as to enhance the discrimination of different clusters and avoid the degeneracy problem. Finally, an entropy regularization technique is incorporated to adaptively refine the affinity graph throughout the clustering process, thereby reducing the sensitivity of clustering performance to the initial affinity graph. Extensive experiments on real-world benchmark datasets demonstrate the superiority of the proposed model over state-of-the-art deep clustering methods.

As optimization algorithms progress to address more complex and high-dimensional challenges, the need for benchmark problems that are both diverse and controllable has become crucial for effective performance evaluation. However, traditional benchmark problem generators often fall short in capturing the required diversity and controllability, limiting their effectiveness in assessing algorithm performance. This paper introduces a novel Controllable Chaotic Landscape Generator (CCLG), designed to enhance the controllability of generated landscapes through the integration of optimization techniques, while maintaining high diversity. This study leverages common problem attributes from the BBOB benchmark suite as targets, enabling effective control over both local and global characteristics of the generated problems, such as the positions of local optima, condition numbers, ruggedness, and global structure. Experimental results demonstrate that CCLG not only achieves effective control over landscape features but also preserves high diversity to meet various optimization requirements.

Facial expression recognition (FER) has recently attracted extensive attention in computer vision. However, existing methods mostly focus on the explicit performance and overlook their computational resources. Hence, achieving competitive performance while maintaining the model efficiency is still a huge challenge. To tackle these issues, we propose a highly lightweight yet effective Channel Shift-Enhancement Gabor-ResNet (CSE-GResNet) to capture the crucial visual properties in facial images. Concretely, we incorporate the Gabor Convolution (GConv) into ResNet to produce the robust GResNet as our backbone with limited memory cost. Furthermore, we propose extremely efficient Channel-Shift Module and Channel-Enhancement Module to insert in the GResNet in cascade. They are adopted to obtain and aggregate the facial informative representation from adjacent channels for extracting the subtle facial expression representation. We conduct extensive experiments on three wild datasets: RAF-DB, FER2013 and SFEW. The results show that the proposed CSE-GResNet achieves superior performance against the state-of-the-art methods with less computational and memory cost.

Symbolic regression represents a critical challenge in computer science, aiming to derive accurate equations for given datasets. The classical symbolic regression algorithm, Neuro-Encoded Expression Programming (NEEP), mitigates the inherent issue of output volatility due to input perturbations caused by the discrete coding in previous evolutionary algorithms. It achieves this by converting discrete coding into continuous coding through neural networks. However, the NEEP model itself confronts two significant challenges. Firstly, it disregards the distance relationships among symbols during the mapping process, thus complicating the post-mapping search. Secondly, it neglects the issue of constant optimization, making the discovery of precise expressions challenging. Addressing these concerns, this study proposes an embedding module during pre-training to impart distance information to symbols, inspired by pre-training methodologies in Natural Language Processing (NLP). This enhancement expedites the search process. Furthermore, to tackle constant optimization challenges, this paper proposes a novel encoding approach to overcome the limitations of traditional placeholder methods that impede expressive capabilities. This new encoding facilitates constant optimization without disrupting the original equation. Experimental results substantiate a significant enhancement in the convergence of DICO-NEEP across various symbolic regression problems.

In Black Box Optimization, traditional Estimation of Distribution Algorithms (EDAs) are limited by strong prior assumptions. To address this, deep generative model-based EDAs, particularly OPT-GAN using Generative Adversarial Networks, show promise due to their adaptability across diverse problems. However, OPT-GAN’s search efficiency and balance between exploration and exploitation remain challenging. This study introduces an improved version of OPT-GAN. By integrating smoothing scale mapping and an adaptive exploration mechanism, it mitigates existing limitations, effectively balancing the E-E trade-off and improving search efficiency. Our experimental results, validated on the COCO benchmark, demonstrate that this improved OPT-GAN outperforms existing neural network-based optimization algorithms, highlighting its potential for wider application in complex optimization scenarios.

A novel fuzzy adaptive knowledge-based inference neural network (FAKINN) is proposed in this study. Conventional fuzzy cluster-based neural networks (FCBNNs) suffer from the challenge of a direct extraction of fuzzy rules that can capture and represent the interclass heterogeneity and intraclass homogeneity when the data possess complex structures. Moreover, the capability of the cluster-based rule generator in FCBNNs may decrease with the increase of data dimensionality. These drawbacks impede the generation of desired fuzzy rules, and affect the inference results depending on the fuzzy rules, thereby limiting their generalization ability. To address these drawbacks, an adaptive knowledge generator (AKG), consisting of the observation paradigm (OP) and clustering strategy (CS), is effectively designed to improve the generalization ability in FAKINN. The OP distills the characteristic information (CI) from data to highlight the homogeneity and heterogeneity of objects, and the CS, viz., the weighted condition-driven fuzzy clustering method (WCFCM), is proposed to summarize the CI to construct fuzzy rules. Moreover, the feedback between the OP and CS can control the dimensionality of CI, which endows FAKINN with the potential to tackle high-dimensional data. The main originality of the study focuses on the AKG and WCFCM that are proposed to develop the structural design methodology of FNNs. The performance of FAKINN is evaluated on various benchmarks with 27 comparative methods, and two real-world problems are adopted to validate its effectiveness. Experimental results show that FAKINN outperforms the comparison methods.

In this study, a novel semantic concept-based inference neural network (SCINN) is proposed to develop the design methodology of the explainable deep neuro-fuzzy models and improve their generalization performance in high-dimensional problems. Traditional neuro-fuzzy models exhibit outstanding interpretability in the problems with lower dimensionality. However, when faced with high-dimensional scenarios, the long rule and rule explosion problems damage their interpretability and result in poor generalization performance (e.g., accuracy), even making them unusable. Although deep neuro-fuzzy models show enhanced performance in handling high-dimensional problems compared to traditional neuro-fuzzy models, they often come at the expense of interpretability. In order to establish the neuro-fuzzy model that is capable of addressing the high-dimensional problems while preserving the interpretability, the SCINN is proposed with the aid of the concept-based measure generation paradigm (CMGP) and the multi-view information augmentation strategy (MIAS). The CMGP is designed to adaptively define the membership functions (MFs) that correspond to the human-understandable semantic concepts based on the given data; the defined MFs contribute to the construction of the explainable fuzzy rule that can directly process high-dimensional data. The MIAS is structured to develop a unified paradigm for implementing consequence functions in the fuzzy rules, which enhances the approximation ability of the SCINN. The performance of SCINN is evaluated on various image datasets using different comparison methods, including neuro-fuzzy-based approaches and deep structure-based neural networks. Furthermore, a real-world application is adopted to evaluate its effectiveness. The experimental results show that SCINN outperforms the compared neuro-fuzzy models and is comparable to the deep structure-based neural network.

In this article, a novel attention-based reinforced interval type-2 fuzzy clustering neural network (ARIT2FCN) is developed to improve the generalization performance of fuzzy clustering-based neural networks (FCNNs). Commonly, fuzzy rules in FCNNs are generated through the clustering-based rule generator. However, the generated fuzzy rules may not be able to fully describe the given data, because the clustering-based rule generator does not simultaneously consider the intracluster homogeneity and intercluster heterogeneity for both of data characteristics and label information when defining membership functions (MFs) of fuzzy rules. This negatively affects fuzzy rules to accurately quantify the interclass heterogeneity and intraclass homogeneity and degrades the performance of FCNNs. The ARIT2FCN is proposed with the aid of the attention-based clustering mechanism and the successive learning method. The attention-based clustering mechanism is designed to define MFs by simultaneously considering data characteristics and label information. The successive learning method is adopted to construct the desired fuzzy rules that can capture the interclass heterogeneity and intraclass homogeneity. Moreover,L$_{2}$norm regularization is used to alleviate the overfitting effect. The performance of ARIT2FCN is evaluated on machine learning datasets with 16 comparative methods. In addition, two real-world problems are adopted to validate the effectiveness of ARIT2FCN. Experimental results demonstrate that the ARIT2FCN outperforms the comparative methods, and the statistical tests also support the superiority of ARIT2FCN.

Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details. Most classical methods for such problems are based on strong and fixed a priori assumptions, such as Gaussianity. However, the complex real-world problems, especially when the global optimum is desired, could be very far from the a priori assumptions because of their diversities, causing unexpected obstacles. In this study, we propose a generative adversarial net-based broad-spectrum global optimizer (OPT-GAN) which estimates the distribution of optimum gradually, with strategies to balance exploration-exploitation trade-off. It has potential to better adapt to the regularity and structure of diversified landscapes than other methods with fixed prior, e.g., Gaussian assumption or separability. Experiments on diverse BBO benchmarks and high dimensional real world applications exhibit that OPT-GAN outperforms other traditional and neural net-based BBO algorithms. The code and Appendix are available at https://github.com/NBICLAB/OPT-GAN

In the age of big data, data has already become a "high-value commodity" with clear price. Privacy leaks can lead to personal information security violations during training in federated learning, especially in the medical industry. The data of the medical industry is characterized by large amount of data and high demand for privacy. For this reason, we designed a Decentralized Reinforced Anonymous Federated Learning Based on Blockchain (DRA-FLchain) with high privacy protection and strong anonymity. In view of the large amount of data in the medical industry, DRA-FLchain uses blockchain technology to enable a large number of clients to participate in model training, and also uses cut through technology to reduce the cost of storage space. DRA-FLchain uses the blockchain and ring signature to ensure the anonymity of the client’s identity, and also uses homomorphic encryption and mask to protect the security of the model. For anonymous Federated Learning (FL), we set up a novel reward mechanism based on game theory Reward mechanism based on ring signature (RMBRS), which can distribute rewards fairly in the anonymous FL architecture. We compared the accuracy and operation efficiency of FL, Federated Learning Based on Blockchain (FLchain) and DRA-FLchain through experiments. The experimental results show that DRA-FLchain is an effective anonymous and secure architecture. Finally, we proved that DRA-FLchain can still protect the privacy of clients well in extreme cases through case study.

Solid texture synthesis (STS), an effective way to extend a 2D exemplar to a 3D solid volume, exhibits advantages in computational photography. However, existing methods generally fail to accurately learn arbitrary textures, which may result in the failure to synthesize solid textures with high fidelity. In this paper, we propose a novel generative adversarial nets-based framework (STS-GAN) to extend the given 2D exemplar to arbitrary 3D solid textures. In STS-GAN, multi-scale 2D texture discriminators evaluate the similarity between the given 2D exemplar and slices from the generated 3D texture, promoting the 3D texture generator synthesizing realistic solid textures. Finally, experiments demonstrate that the proposed method can generate high-fidelity solid textures with similar visual characteristics to the 2D exemplar.

In order to further improve the convergence properties of generative adversarial networks, in this paper, we analyze how the stability can be affected by the so-called best-effort manner of the discriminator in the minimax game. We point out that this manner can cause the multistate problem and the optimization entangling problem. To alleviate these, we proposed an alternative least-effort loss to regularize the training behaviors of the discriminator. With this loss, the discriminator only updates when it is unable to distinguish distributions. To evaluate the effectiveness of the least-effort loss, we introduce it into Wasserstein GAN. Experiments on Dirac delta distribution and image datasets demonstrate that the least-effort loss can effectively improve the convergence properties and generation quality of WGAN. Furthermore, the behaviors of the discriminator and generator during the training show that, with the least-effort loss, the state space of the discriminator shrinks, and the optimization of the discriminator and the generator disentangles in some way.

Learning with noisy labels is one of the most challenging tasks in semi-supervised learning, and it poses significant problems in various practical applications. In the network learning process, the noisy labels concealed in the training dataset are easy to remember, resulting in poor generalization performance. To overcome this problem, inspired by the correction ability of humans – “think and learn from the past,” an end-to-end dynamic correction framework against label noise called Reflective Learning (RL) is proposed. This solution incorporates valuable knowledge from the past network training process to assist in correcting noisy labels. Specifically, during network training, a dynamic iterative function is implemented to adaptively correct noisy labels by employing the network’s predictive distribution information of all training epochs. This dynamic iterative function takes the form of a Standard Normal Distribution function to effectively match the changes of noisy label correction information contained in the network’s predictive probabilities. The proposed method is general and applicable to any backbone network and different types of noise without auxiliary information. Experiments are conducted on datasets with synthetic and real-world label noise datasets, including CIFAR-10, CIFAR-100, Tiny-ImageNet, and Clothing1M. They demonstrate that the proposed method is superior to the state-of-the-art results.

Distributed clustering based on the Gaussian mixture model (GMM) has exhibited excellent clustering capabilities in peer-to-peer (P2P) networks. However, more iterative numbers and communication overhead are required to achieve the consensus in existing distributed GMM clustering algorithms. In addition, the truth that it cannot find a closed form for the update of parameters in GMM causes the imprecise clustering accuracy. To solve these issues, by utilizing the transfer learning technique, a general transfer distributed GMM clustering framework is exploited to promote the clustering performance and accelerate the clustering convergence. In this work, each node is treated as both the source domain and the target domain, and these nodes can learn from each other to complete the clustering task in distributed P2P networks. Based on this framework, the transfer distributed expectation-maximization algorithm with the fixed learning rate is first presented for data clustering. Then, an improved version is designed to obtain the stable clustering accuracy, in which an adaptive transfer learning strategy is adopted to adjust the learning rate automatically instead of a fixed value. To demonstrate the extensibility of the proposed framework, a representative GMM clustering method, the entropy-type classification maximum-likelihood algorithm, is further extended to the transfer distributed counterpart. Experimental results verify the effectiveness of the presented algorithms in contrast with the existing GMM clustering approaches.

Kernel clustering has the ability to get the inherent nonlinear structure of the data. But the high computational complexity and the unknown representation of the kernel space make it unavailable for the data clustering in distributed peer-to-peer (P2P) networks. To solve this issue, we propose a new series of random feature-based collaborative kernel clustering algorithms in this article. In the most basic algorithm, each node in a distributed P2P network first maps its data into a low-dimensional random feature space with the approximation of the given kernel by using the random Fourier feature mapping method. Then, each node independently searches the clusters with its local data and the collaborative knowledge from its neighbor nodes, and the distributed clustering is performed among all network nodes until reaching the global consensus result, i.e., all nodes have the same cluster centers. In addition, an improved version is designed with assignment of feature weights, which is optimized by the maximum-entropy technique to extract important features for the cluster identification. What’s more, to relief the impact of different kernel functions and related parameters on clustering results, the combination of multiple kernels rather than a single kernel is adopted for the low-dimensional approximation, and the optimized weights are assigned to provide the guidance on the choice of the kernels and their parameters and discover significant features at the same time. Experiments on synthetic and real-world datasets show that the proposed methods achieve similar and even better results than the traditional kernel clustering methods on various performance metrics, including the average classification rate, the average normalized mutual information, and the average adjusted rand index. More importantly, the low-dimensional random features approximated to kernels and the distributed clustering mechanism adopted in these methods bring the greatly lower temporal complexity.

Cement has been widely used in civil engineering directly and plays a critical role in cement-based materials, e.g., concrete. As the microstructural evolution of cement hydration predominates the final physical properties, an accurate simulation of hydration is highly required to enable scientists to evaluate the performance and help design new cementitious materials. However, despite significant effort and progress, a satisfactory model to realistically and accurately simulate the evolution of three-dimensional (3-D) microstructure has not yet to be constructed, mainly because cement hydration is one of the most complex phenomena in material science. In this work, a novel near-realistic microstructural model is proposed to simulate the cement hydration system using deep learning and cellular automata. It is designed to break through the bottleneck of fidelity to real microstructural evolution. The dynamical system is constructed based on a 3-D cellular automaton, in which behavior is controlled by deep neural networks distilled from microstructural images. In addition, a dynamic stratified sampling method with variable capacity is proposed to ensure the representativeness of samples for reducing the computation cost of training. Experiments manifest that the simulated hydration is in accordance with the actual development in different aspects, such as near-realistic microstructure and approximate process. Furthermore, the constructed system also demonstrates promising generalization capability even under various conditions.

In recent years, kernel-based fuzzy clustering has attracted significant attention, primarily benefiting from the outstanding performance of capturing the potential non-linear structure in data clustering. However, many existing kernel clustering methods are not available for large datasets due to computational costs. To overcome this limitation, the low-rank random feature map is utilized to approximate the kernel space. Nevertheless, this kind of feature approximation method ignores the graph structure information hidden in the data and does not take the correlations between data samples in the clustering into account. Thus, we present a new kernel fuzzy clustering based on Quasi-Monte Carlo feature map with neighbor affinity constraint (Na_QMC_KFC). In this scheme, the Quasi-Monte Carlo method is adopted to approximate the Gaussian kernel function so as to reduce the computational costs. Meanwhile, the neighbor affinity constraint is designed to maintain the graph structure information of the data and further facilitate the consistency of the membership degrees and the raw data. What’s more, the Alternating Direction Method of Multipliers method is utilized to optimize the problem with respect to the neighbor affinity lasso. The experiments on several non-linear and real-world datasets exhibits the efficiency of the presented algorithm.

Facial expression recognition (FER) has recently attracted attention in computer vision. However, existing methods mostly focus on the explicit performance and overlook their computational resources and memory consumption. Hence, achieving promising performance while maintaining the efficiency of models is still a huge challenge. In this work, we propose a highly efficient Channel-Shift Gabor-ResNet (CS-GResNet) to capture the crucial visual properties in facial images. Concretely, we incorporate the Gabor Convolution (GConv) into ResNet to produce the significant GResNet as our backbone with limited memory cost. Furthermore, we adopt an extremely simple yet effective Channel-Shift Module inserted into the GResNet to obtain the facial informative representation via facilitating information exchanged among neighboring channels. We conduct extensive experiments on three wild datasets: RAF-DB, FER2013 and SFEW. The results show that our proposed CS-GResNet achieves superior performance against the state-of-the-art methods with less computational and memory cost. Codes are available at https://github.com/jsesr/CS-GResNet-PyTorch.

There is an increasing interest in enhancing the quality of low-resolution (LR) facial images for various social life applications. Existing methods often use domain-specific prior knowledge, which is effective in improving the face super-resolution model's performance. However, it is challenging to obtain rich and accurate prior information from LR inputs in real-world scenarios, which can limit the robustness and generalization ability of the developed face super-resolution model. In this paper, a multisource reference-based face super-resolution Network, namely MSRNet, is proposed. Without considering the prior knowledge of faces, the network can reconstruct a LR face image with a magnitude factor of 8 under the guidance of multiple reference face images of different identities. By constructing an “appearance-alike” reference data set Face_Ref, the designed MSRNet aims to fully exploit the local and spatially similar high frequency information between the distinct references and the current face. More specifically, to effectively combine the information from multiple references, a cross-scale and cross-space feature fusion mechanism is introduced for external and internal references, and then the enhanced local semantics are finally incorporated into the high-resolution face reconstruction. The robustness of face image super-resolution is increased compared to current correlation approaches, since it not only eliminates the need for face prior knowledge but also avoids performing alignment operations on reference faces with multiple expressions and different poses. Experimental results show that the proposed model is able to produce results for face super-resolution that are satisfying and dependable and outperforms the state-of-the-art methods in terms of visual perceptual quality and quantity evaluation.

In this article, a fuzzy floating centroids method (FFCM) is proposed, which uses a fuzzy strategy and the concept of floating centroids to enhance the performance of the neural-network classifier. The decision boundaries in the traditional floating centroids neural-network (FCM) classifier are "hard." These hard boundaries force a point, such as noisy or boundary point, to be assigned to a class exclusively, thereby frequently resulting in misclassification and influencing the performance of optimization methods to train the neural network. A fuzzy strategy combined with floating centroids is introduced to produce "soft" boundaries to handle noisy and boundary points, which increases the chance of discovering the optimal neural network during optimization. In addition, the FFCM adopts a weighted target function to correct the preference to majority classes for imbalanced data. The performance of FFCM is compared with ten classification methods on 32 benchmark datasets by using indicators: average F -measure (Avg.FM) and generalization accuracy. Also, the proposed FFCM is applied to nondestructively estimate the strength grade of cement specimens based on microstructural images. In the experimental results, FFCM achieves the optimal generalization accuracy and Avg.FM on 17 datasets and 21 datasets, respectively; FFCM balances precision and recall better than its competitors for the estimation of cement strength grade.

In this study, a novel promotive particle swarm optimizer with double hierarchical structures is proposed. It is inspired by successful mechanisms present in social and biological systems to make particles compete fairly. In the proposed method, the swarm is first divided into multiple independent subpopulations organized in a hierarchical promotion structure, which protects subpopulation at each hierarchy to search for the optima in parallel. A unidirectional communication strategy and a promotion operator are further implemented to allow excellent particles to be promoted from low-hierarchy subpopulations to high-hierarchy subpopulations. Furthermore, for the internal competition within each subpopulation of the hierarchical promotion structure, a hierarchical multiscale optimum controlled by a tiered architecture of particles is constructed for particles, in which each particle can synthesize a set of optima of its different scales. The hierarchical promotion structure can protect particles that just fly to promising regions and have low fitness from competing with the entire swarm. Also, the double hierarchical structures increase the diversity of searching. Numerical experiments and statistical analysis of results reported on 30 benchmark problems show that the proposed method improves the accuracy and convergence speed especially in solving complex problems when compared with several variations of particle swarm optimization.

The traditional collaborative fuzzy clustering can effectively perform data clustering in distributed peer-to-peer networks, which is an impossible task to complete for the centralized clustering methods due to privacy and security requirements or network transmission technology constraints. But it will increase the number of clustering iterations and lead to lower efficiency of the clustering. Moreover, the collaborative mechanism hidden in the iterative process of clustering cannot be well revealed and explained. In this article, a novel series of transfer collaborative fuzzy clustering algorithms are proposed to solve these issues. In the first basic algorithm, the transfer learning among neighbor nodes vividly expresses the collaborative mechanism and enhances the information collaboration to accelerate the convergence of fuzzy clustering. Meanwhile, neighbor nodes can learn the knowledge from each other to further promote their respective clustering performance. Then, an improved version, with the learning-rate-adjustable strategy instead of fixed values, is designed to highlight the different influence between neighbor nodes, and the appropriate learning rates between neighbor nodes are achieved to ensure the stable clustering accuracy. Finally, two extended versions with the attribute-weight-entropy regularization technique are presented for the clustering of high dimensional sparse data and the extraction of important subspace features. Experiments show the efficiency of the proposed algorithms compared with the related prototype-based clustering methods.

Cement has been widely used in civil engineering, whose quality directly affects the safety of buildings. Cement compressive strength, as an important quality indicator, its accurate estimation is of great significance in quality inspections and the design of high-performance products. However, existing measurement technology remains traditional and destructive. Except for high time-consuming and the waste of various resources, it requires significant improvement since the unprofessional operations will give rise to large errors. In this article, an efficient system is proposed to estimate the cement compressive strength based on the broad learning and internal factors, in which the index system describes the internal factors affecting the compressive strength, and the broad learning system distills the potential correlation between the compressive strength and those factors. It can nondestructively estimate the strength directly with the internal factors, e.g., clinker composition and physical properties. In addition, to verify its practicability and to assist the formula optimization in the application, the robustness test and factorial analysis are designed. The experimental results prove that this model can accurately estimate the strength with excellent generalization ability, which saves labor power and material, avoids large errors caused by unprofessional operations, and aids high-performance cement production. Especially, its ability to rapidly build an accurate estimation model is beneficial for the production of various cement in industry.

Facial expression recognition (FER) has recently attracted much attention in computer vision. However, existing methods mostly focus on the texture information of faces and overlook their inherent topological features. Hence more informative and significant contents are ignored for expression recognition. In this work, we propose a Two-stream Gabor-AGraph Convolutional Network (2s-GAGCN) to exploit the facial texture and topological features simultaneously. The Gabor Stream and the Attention-Graph (AGraph) Stream are respectively introduced to capture the salient visual properties and discriminative landmark features of faces. In particular, we adopt a flexible node attention mechanism in AGraph Stream through utilizing global and local information to enhance the potential relationships among landmarks. Furthermore, a novel landmark feature descriptor is proposed to alleviate the redundant topological features, which shows promising improvement for the recognition accuracy. We conduct extensive experiments on two wild datasets: RAF-DB and SFEW. The results show that the proposed 2s-GAGCN achieves superior performance against the state-of-the-art methods.

Facial expression recognition (FER) in the wild is an important yet challenging problem because of uncontrolled conditions, such as occlusions, pose, and illumination. Most existing methods utilize the global and local information, but ignore the potential correlation between the global and local faces. In this paper, we propose a two-stream global-guided attention network (TGGAN) for FER in the wild. To further exploit the complementary relationship between local and global, we design a global-guided attention module (GGAM). Especially, a global guidance mechanism is proposed in GGAM to utilize the global information to guide the capture of key local features. Furthermore, inspired by the transformer, a self-attention mechanism is introduced in GGAM to emphasize salient face regions and fully integrate features extracted from global and local streams. We validate the proposed TGGAN on two wild datasets (FERPlus, RAF -DB) and further conduct experiments on their test subsets of occlusion and multi-poses. Extensive experiments show that the proposed TGGAN achieves superior performance against the state-of-the-art methods.

Neural network optimization relies on the ability of the loss function to learn highly discriminative features. In recent years, Softmax loss has been widely used to train neural network models in various tasks. In order to further enhance the discriminative power of the learned features, Center loss is introduced as an auxiliary function to aid Softmax loss jointly reduce the intra-class variances. In this paper, we propose a novel loss called Differentiable Magnet loss (DML), which can optimize neural nets independently of Softmax loss without joint supervision. This loss offers a more definite convergence target for each class, which not only allows the sample to be close to the homogeneous (intra-class) center but also to stay away from all heterogeneous (inter-class) centers in the feature embedding space. Extensive experimental results demonstrate the superiority of DML in a variety of classification and clustering tasks. Specifically, the 2-D visualization of the learned embedding features by t-SNE effectively proves that our proposed new loss can learn better discriminative representations.

In this article, the fault-tolerant control (FTC) problem of vehicle active suspension is concerned in the discrete-time domain, in which the road disturbances and faults in actuator and measurement are considered. The main contribution consists of proposing an active physically realizable fault-tolerant controller based on a reduced-order observer, which makes up an optimal vibration control component and an event-triggered FTC component. More specifically, by discussing a discrete vehicle active suspension subject to road disturbances generated from the output of a designed exosystem, the optimal vibration control component is derived from maximum principle to offset the inevitable vibrations. Meanwhile, based on the real-time system output of vehicle suspension rather than residual error, a reduced-order observer is proposed to cover the physically unrealizable problem for the designed optimal vibration control component. After that, an event-triggered FTC component and an event-triggered restructured system output are designed to compensate the faults in actuator and measurement, respectively. Finally, extensive experiments are conduced to the control performance of vehicle active suspension under the proposed controller, and confirm its effectiveness and superiority over other control schemes.

Particle swarm optimization (PSO) in recent years has been widely applied to solve various real world problems. However, for ill conditioned problems with largely different sensitivity to the objective function, classical PSO cannot search for optimal solution efficiently due to the best position-guided strategy that wastes lots of source searching undesirable areas. Therefore, this paper proposes a novel velocity reinforced mechanism (VR) for solving m-conditional problems. Two implementations of the mechanism, velocity reinforced particle swarm optimization and velocity reinforced search, are introduced in this paper. VR updates its velocity by learning and correcting best velocity directly, instead of using classical best position-guided updating rules. In this way, it increases the possibility that finds better directions for m-conditional problems. Experiments indicate that the novel approaches improve the final results and efficiency.

The cosine-based softmax loss functions greatly enhance intra-class compactness and perform well on the tasks of face recognition and object classification. Outperformance, however, depends on the careful hyperparameter selection. Adaptively Scaling Cosine Logits (AdaCos) tries to propose a parameter-free version by leveraging an adaptive scaling parameter. Nevertheless, the application of AdaCos is limited in specific domains because of improper approximation.In this paper, to promote intra-class compactness and interclass separability, we propose an Angular Gradient Margin Loss (ArcGrad) that generates a gradient margin by maximizing the angular gradient. Our work suggests that the margin parameter on cosine-based methods is not necessary, and the scaling parameter is inversely proportional to the margin. Furthermore, a stable and large gradient promotes better feature representation. In experiments, we test our method, as well as other methods enhancing discriminative information, on CIFAR and 15 datasets from UCI. Experimental results show ArcGrad consistently outperforms both on large and small scale problems and has the superiority in discriminative information and time-consumption.

Classical benchmark problems utilize multiple transformation techniques to increase optimization difficulty, e.g., shift for anti centering effect and rotation for anti dimension sensitivity. Despite testing the transformation invariance, however, such operations do not really change the landscape's "shape", but rather than change the "view point". For instance, after rotated, ill conditional problems are turned around in terms of orientation but still keep proportional components, which, to some extent, does not create much obstacle in optimization. In this paper, inspired from image processing, we investigate a novel graphic conformal mapping transformation on benchmark problems to deform the function shape. The bending operation does not alter the function basic properties, e.g., a unimodal function can almost maintain its unimodality after bent, but can modify the shape of interested area in the search space. Experiments indicate the same optimizer spends more search budget and encounter more failures on the conformal bent functions than the rotated version. Several parameters of the proposed function are also analyzed to reveal performance sensitivity of the evolutionary algorithms.

For image segmentation, fuzzy clustering methods with single spatial information cannot ensure robustness to the image corrupted by different noises. In this paper, to figure out this problem, we propose a multiple spatial information weighted fuzzy clustering method, in which the original pixel intensity and its two spatial information, the mean and median of neighbors within a local window, are combined with different weights to obtain precise segmentation results of noise images. And the entropy-regularized method is employed to optimize the weight of each term to handle the images with different noise. What's more, the kernelization of the proposed method is presented to relief the impact of outliers. It is worth noting that our methods can be further extended by combining with other spatial information. Experiments on synthetic images and natural images show the superiority and efficiency of the proposed methods.

Chinese herbal medicine is an important part of traditional Chinese medicine (TCM). With developing of traditional Chinese medicine, the usage of Chinese herbal medicine is growing rapidly. It is essential to identify Chinese herbal medicine correctly since Chinese herbal medicine is used to treat disease. However, identifying Chinese herbal medicine is a hard task because lots of Chinese herbal medicine with different properties displays similar appearance, such as Radix StephaniaeTetrandrae and Radix Paeoniae Alba. Traditional methods of classifying Chinese herbal medicine are low-efficiency and rely on professional medical knowledge. Machine learning methods can reduce the need for professional knowledge in some fields due to its self-learning ability. In this study, a framework, called CNN & BLS, combining the convolutional neural network (CNN) with broad learning system (BLS) for identifying the Chinese herbal medicine, is proposed. Experimental results show the CNN & BLS displays the promising performance for identifying Chinese herbal medicine.

The centralized longitudinal control problem for Cooperative Adaptive Cruise Control (CACC) systems is discussed in this paper, in which the imperfect wireless communication surroundings and actuator dynamics are taken into consideration. From the large-scale system standpoint, the centralized longitudinal control problem for platoon vehicles equipped with CACC functionality is formulated as minimizing a quadratic performance index under the constrains of a large-scale discrete-time system with actuator delay and system output delay, in which the leader vehicle is set as the control center. After that, benefiting from a designed delay-free transformed vector, a delay-free two-point-boundary-value problem is derived from the equivalent reconstruction forms for original system delay model and performance index. Thus the centralized longitudinal controller is obtained by solving a Riccati equation. Finally, simulation results demonstrate that the ego vehicle can reasonable response the accelerating or decelerating behaviors of the preceding vehicles under the proposed controller, thereby the desired CACC control performance is satisfied, and the wireless communication delay and actuator delay are compensated effectively.

The processes of evolution and learning interact. Learning is an evolved strategy that improves fitness, especially in a world where some aspects cannot realistically be encoded in the genome. We endeavored to see if evolution could sculpt a generic neuroplasticity mechanism into a learning rule that would give virtual organisms an advantage in a simulated foraging environment. Our virtual organisms have brains with nine neurons. The connections between those neurons are adjusted by a plasticity rule that is computed by another fixed neural network. Evolution experiments repeatedly found plasticity networks that conferred an adaptive advantage, even outperforming populations that were given a parametric Hebbian plasticity mechanism. Evolution also favored the inclusion of genetically encoded heterogeneity. We also investigate how behavior is influenced by various brainand movement-related energy penalty terms in the fitness function.

The floating centroids method (FCM) effectively enhances the performance of neural network classifiers. However, the problem of optimizing the neural network continues to restrict the further improvement of FCM. Traditional particle swarm optimization algorithm (PSO) sometimes converges to a local optimal solution in multimodal landscape, particularly for optimizing neural networks. Therefore, the dynamic multilayer PSO (DMLPSO) is proposed to optimize the neural network for improving the performance of FCM. DMLPSO adopts the basic concepts of multi-layer PSO to introduce a dynamic reorganizing strategy, which achieves that valuable information dynamically interacts among different subswarms. This strategy increases population diversity to promote the performance of DMLPSO when optimizing multimodal functions. Experimental results indicate that the proposed DMLPSO enables FCM to obtain improved solutions in many data sets.

The safety of building facilities is directly affected by the physical properties of cement, among which cement compressive strength plays the most important role in evaluating them. Therefore, the investigation of cement compressive strength is helpful in improving the cement properties. Traditionally, chemical composition, curing condition, and water-cement ratio are used to estimate the strength of cement paste. However, this approach is limited by the extreme complexity of physical changes and chemical reactions during cement hydration. Considering the cement microstructure contains information related to strength microscopically, microtomography, which can image three-dimensional microstructure, provides scientists with another way to study cement compressive strength nondestructively. This study estimates cement compressive strength using microstructure features extracted from microtomography images and gene expression programming. A probabilistic polarized similarity weight tournament selection operator is also proposed to balance the exploration and exploitation. Experimental results corroborate that the obtained relationship possesses higher estimation accuracy, good interpretability and the evolutionary capability performs well.

In recent years, the scale and diversity of malicious software on mobile networks are constantly increasing, thereby causing considerable danger to users' property and personal privacy. In this study, we devise a method that uses the URLs visited by applications to identify malicious apps. A multi-view neural network is used to create a malware detection model that emphasizes depth and width. This neural network can create multiple views of the input automatically and distribute soft attention weights to focus on different features of input. Multiple views preserve rich semantic information from input for classification without requiring complicated feature engineering. In addition, we conduct comprehensive experiments to compare the proposed method with others and verify the validity of the detection model. The experimental results show that our method has a certain timeliness. It can not only effectively detect malware discovered in different months of a certain year, but also detect potentially malicious apps in the third-party app market. We also compare the detection results of the proposed method on wild apps with 10 popular anti-virus scanners, and the final result shows that our approach ranks second in terms of detection performance.

The microstructure images of cement are often used as the main data source for estimating compressive strength. They contain ample physical properties during the hydration process. Different gray values represent different substances in the grayscale image of cement. Deep learning algorithm based on microstructure images have been proposed to estimate cement compressive strength (CCS). However, there are a large number of parameters that need to be adjusted in deep structure. The high-efficiency system named broad learning system (BLS) is tried to use to estimate the cement compressive strength. The original cement microstructure images and the extracted features are used as input respectively, the connection weights can be obtained directly by calculating pseudo inverse matrix of feature matrix of microstructure image. If the structure is not sufficient to gain suitable result, BLS only calculates the pseudo inverse matrix of additional nodes to improve accuracy. The experiment shows that the broad learning structure (BLS) is an effective and efficient method on estimating cement compressive strength by contrasting with deep learning structure.

Visual sentiment analysis of online user generated content is important for many social media analysis tasks. However, label noise is common in sentiment analysis datasets, which deteriorate classification performance. To address this issue, we propose a novel visual sentiment analysis method based on loss reweighting to improve model robustness for label noise. First, a CNN is pre-trained with softmax loss on noisy labels datasets. Second, noise matrix is estimated by resorting and repositioning predicted probability, which is predicted by the pre-trained CNN. Third, converting noise estimation to the loss weight, the degeneration of sentiment classifiers performance caused by noisy labels can be compensated by re-training neural network with this reweighing loss. We conduct experiments on public sentiment datasets including Sentibank and Twitter datasets, and demonstrate that the proposed method outperforms state-of-the-art results.

In recent years, the number and variety of malicious mobile apps have increased drastically, especially on Android platform, which brings insurmountable challenges for malicious app detection. Researchers endeavor to discover the traces of malicious apps using network traffic analysis. In this study, we combine network traffic analysis with machine learning methods to identify malicious network behavior, and eventually to detect malicious apps. However, most network traffic generated by malicious apps is benign, while only a small portion of traffic is malicious, leading to an imbalanced data problem when the traffic model skews towards modeling the benign traffic. To address this problem, we introduce imbalanced classification methods, including the synthetic minority oversampling technique (SMOTE) + support vector machine (SVM), SVM cost-sensitive (SVMCS), and C4.5 cost-sensitive (C4.5CS) methods. However, when the imbalance rate reaches a certain threshold, the performance of common imbalanced classification algorithms degrades significantly. To avoid performance degradation, we propose to use the imbalanced data gravitation-based classification (IDGC) algorithm to classify imbalanced data. Moreover, we develop a simplex imbalanced data gravitation classification (S-IDGC) model to further reduce the time costs of IDGC without sacrificing the classification performance. In addition, we propose a machine learning based comparative benchmark prototype system, which provides users with substantial autonomy, such as multiple choices of the desired classifiers or traffic features. Using this prototype system, users can compare the detection performance of different classification algorithms on the same data set, as well as the performance of a specific classification algorithm on multiple data sets.

Spectral clustering is one of the most effective methods of data mining, in which the adjacency matrix is constructed by using the similarity matrix. In this paper, to extend spectral clustering method for uncertain data clustering, we propose a new spectral clustering method based on JS-divergence. In the proposed method, the JS-divergence is used to construct the adjacency matrix in the spectral clustering, which is more suitable to calculate the similarity between uncertain data objects as a symmetrical measurement compared to the KL-divergence.

This paper presents a nearest neighbor partitioning method designed to improve the performance of a neural-network classifier. For neural-network classifiers, usually the number, positions, and labels of centroids are fixed in partition space before training. However, that approach limits the search for potential neural networks during optimization; the quality of a neural network classifier is based on how clear the decision boundaries are between classes. Although attempts have been made to generate floating centroids automatically, these methods still tend to generate sphere-like partitions and cannot produce flexible decision boundaries. We propose the use of nearest neighbor classification in conjunction with a neural-network classifier. Instead of being bound by sphere-like boundaries (such as the case with centroid-based methods), the flexibility of nearest neighbors increases the chance of finding potential neural networks that have arbitrarily shaped boundaries in partition space. Experimental results demonstrate that the proposed method exhibits superior performance on accuracy and average f-measure.

One of the main tasks in neuroscience research is to interpret the activity of neurons. Given some neuroscientific data, such as spike trains, one tries to decipher how the activity of the neurons relate to the outside world and/or the behaviour of the animal. The discovery of place cells and grid cells are great examples - discoveries that garnered a Nobel Prize in 2014. However, the spatial patterns exhibited by such cells are only the beginning of our understanding of spatial representation in the brain. In this paper, we apply an evolutionary algorithm to discover spatial patterns exhibited in cells from the entorhinal cortex to see (1) if we can automatically deduce an accurate model for the hexagonal-grid pattern, and (2) if we can discover a more general model that also incorporates grid-cell-like variants that have been observed, but not understood.

Evolution is extremely creative. The mere availability of a mechanism for synaptic change seems to be enough for evolution to derive a learning rule. Many simulations of evolution have evolved learning in a highly guided manner. Either by constraining the update function to a Hebbian form, or by supplying an error/teaching signal. In this paper, we aim to evolve a more general learning rule. And since neural networks are so versatile, we construct the learning function itself out of a neural network. Our evolved networks excel at the foraging task they evolved in. Amazingly, they even function robustly when tested outside of their historical niche. The same cannot be said for the Hebbian learning networks we compare to.

This paper considers the sliding mode control (SMC) for a class of state delayed systems subject to persistent disturbances. First, a disturbance compensator is proposed to eliminate the influence from persistent disturbances, and the stability of control system is discussed. Then, the control problem is transformed into sliding mode control problem for state delayed system without expression of disturbances. The reduced-order sliding mode surface function is proposed based on the Lyapunov-Functional and the designed switching function. Furthermore, sliding mode control law is obtained. Finally, the simulation results demonstrate that the proposed control law can guarantee the stability of state delayed systems.

In gene expression programming, diversity can be reduced during evolution, sometimes resulting in premature convergence because of non-coding regions, leading to substantial reproduction of repeated individuals. In order to increase the diversity of the population and to avoid premature convergence, we propose a new diversity preservation tournament operator, adopting a tree-based similarity measurement and global probability weights. Furthermore, the proposed tournament operator is embedded into a hybrid evolution architecture to search for a parsimonious model for the firing pattern of grid cells, neurons in the mammalian brain involved in navigation. Experimental results demonstrate that the proposed diversity preservation tournament improves the performance of gene expression programming for evolving a model for grid-cell data.

The physical properties of cement are strongly influenced by the development of microstructure and cement hydration. Therefore, the investigation of microstructure for cement paste enables us to understand the hydration process and to predict the physical properties. However, the unreliability of phase classification and segmentation in an image affect the description of microstructure, as well as the prediction of properties and the simulation of hydration. This paper studies the dynamic relationship between microstructure and physical properties from the image itself. The relationship between compressive strength and microstructure image features is built as the form of image feature kinetics using gene expression programming from observed microtomography images. A similarity weight tournament selection is also proposed to increase the diversity of population and improve the performance. Experimental results manifest that the evolved image feature kinetics not only perform well in fitting training data but also exhibit superior generalization ability.

The particle swarm optimization, inspired by nature, is widely used for optimizing complex problems and achieves many good stories in practical applications. However, the traditional PSO only focuses on the function value during evolutionary process. It ignores the information of distance between particles and potential regions. A Dual Factors Particle Swarm Optimization (DFPSO) incorporating both of distance and function information is proposed in this paper to help PSO in finding potential global optimal regions. The strategy of the DFPSO increases the diversity of population to yield improved results. The experimental results manifest that the performance, including accuracy and speed, are improved.

The hydration of cement is a complex process with chemical and physical interaction and it has an important impact on the formation of microstructure and development of strength. In this paper, we designed a collaborative hybrid evolutionary method to infer cement hydration model from observed cement hydration time series data using ordinary differential equations (ODE).The structure of the ODE is inferred by multi-layers multi-expression programming(MMEP) , the ODE's parameters are optimized through particle swarm optimization (PSO) and the forth-order Runge-Kutta(RK4) is used to solve the differential equation. Numerical experiments showed that the proposed method could acquire the structure of differential equation within short generations. Cement experiment on the degree of hydration model illustrated that the cement hydration model could simulate the process of hydration effectively.

This paper presents a longitudinal tracking control law for Cooperative Adaptive Cruise Control (CACC) systems in a platoon that can comprehensively enable tracking capability of various spacing policies, designed expected velocity, and designed expected acceleration. Taking into account heterogeneous traffic, i.e., a platoon of vehicles with possibly different characteristics, the longitudinal control problem is formulated as an output tracking control problem with a quadratic function so that the contradictions among the different tracking requirements are realized, which include inter-vehicle spacing, velocity and acceleration. Then, the decentralized longitudinal tracking control law is proposed by using a limited communication structure and maximum principle (in this case, a wireless communication link with the nearest preceding vehicle and designed platoon leader only), in which the feedback items are composed of the states of host vehicles, and additional information of the nearest preceding vehicle and designed platoon leader are used as feed forward items. In addition, the concepts of "expected velocity" and "expected acceleration" are introduced to design the desired velocity and acceleration, realize additional objectives, and improve the predictive abilities. Numerous simulation results show that the proposed tracking controller provides a reliable tool for a systematic and efficient design of a platoon controller within CACC systems.

Concrete is viewed as the most important cement-based composite material in the field of civil engineering. Its strength is considered the most important among its mechanical properties. Although the value of strength can be directly forecasted, the estimation of strength grade remains particularly important because concrete mortar is non-uniform, and practical preparation and curing cannot be fully simulated under laboratory conditions. In this paper, concrete strength grade was predicted by using the floating centroids method neural network classifier, which removes the fixed-centroid constraint and increases the possibility of finding an optimal neural network. Experimental results show that concrete strength prediction performance is improved by employing the floating centroids method.

The hydration of Portland cement paste has an important impact on the formation of microstructure and development of strength. Manual derivation of cement hydration kinetic equation is very difficult because of the extreme complexity in Portland cement hydration. It can be reversely extracted automatically from the observed time series using evolutionary computation method. However, the physical meaning of coefficients of the extracted kinetic equation can not be understood easily, which limits the scope of application of kinetic equation in predicting hydration reaction. In this paper, in order to predict the reaction process of Portland cement, an evolutionary approach to predict the development of cement hydration using extreme early-age data and differential evolution algorithm is proposed. The experimental results indicate that the proposed method is very suitable for the forecasting of the development of degree of hydration for Portland cement.