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.

Network traffic classification plays an indispensable role in network management, Quality of Service (QoS), and cybersecurity. With the widespread encryption techniques applied to network traffic, it has become increasingly challenging to classify network traffic into different management groups accurately. In recent years, pre-training Transformer-based models have been successfully applied to Natural Language Processing (NLP), and researchers have also introduced such models into encrypted network traffic analysis. However, besides the similarities of words in NLP and byte codes in network traffic, there exist essential differences between them, which may cause inefficacy of the pretrained model when being applied to new traffic data. In this paper, we propose a non-pretrained encrypted network traffic classification model based on Transformer called NT-Transformer, which can directly learn labeled network traffic features at two levels of granularity, namely, byte level (uni-gram or bi-gram) and flow level (packet size and packet inter-arrival time), without the relatively expensive pre-training procedure of unlabeled data. This method is validated on three public datasets and three sets of recently collected network traffic data. Experimental results indicate that in some scenarios, pretrained models offer limited performance gains when applied to new encrypted network traffic data not encountered during pretraining, and NT-Transformer with uni-gram byte representation outperforms the state-of-the-art models in terms of pushing the F1 score up by 0.25% - 2.24%.

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.

The multi-label text classification (MLTC) task involves associating text data with multiple relevant labels. However, previous studies often overlooked the co-occurrence information of labels within text, resulting in the inability to distinguish similar labels. Moreover, these studies have underestimated the importance of label node initialization. To tackle these challenges, we propose a Label-aware Multi-semantic Fusion Network (LMFN). Our approach employs label-guided attention to learn text representations closely aligned with labels. Then, in order to obtain more refined semantic representation, the word embedding matrix is introduced to integrate features from diverse sources. Concurrently, we use joint learning network to extract label features. We first initialize label nodes and use multi-layer GCNs to capture the dependencies and higher-order information between labels. Following this, cross-attention is utilized to effectively integrate label features with internal semantics and reveal latent correlations. Comprehensive experiments on two standard datasets show that our proposed model LMFN outperforms existing methods.

Fact-checking is a highly challenging task that requires verifying the truthfulness of a claim based on multiple evidence sentences. Despite the effectiveness of existing methods, they overlook the differences in the importance of various news entities. Additionally, they fail to consider the semantic relationships between the claim and the evidence from multiple perspectives. To address these issues, we propose an Entity-aware Multi-perspective Semantic Fusion Network (EMSFN) for Fact-checking Fake News Detection. First, we introduce the Entity Attention Network to extract semantic information from claim and calculate the differences in the importance of entities. Then, we built the Multi-view Semantic Relation Extraction Network to capture the interactions between claim and evidence, extracting multi-dimensional interaction information. The proposed EMSFN calculates the contribution degree of different entities and facilitates information interaction between claim and evidence from multiple perspectives. Experiments on Snopes and PolitiFact datasets validate the effectiveness of our EMSFN.

Micro-computed tomography (μCT), a powerful three-dimensional non-destructive imaging device, enables the acquisition of detailed microstructural images, which provides essential data for in-depth analysis of the cement microstructure during hydration. However, acquiring high-resolution μCT images of the cement hydration microstructure is challenging due to the high cost of equipment with high resolution, ongoing maintenance expenses, and lengthy scan times. Additionally, the sample size limits the resolution because smaller samples fail to represent the realistic state of cement hydration, while larger samples cannot be effectively penetrated by X-rays. This study proposes a transformer-based high-resolution μ-CT image reconstruction method for cement hydration, which provides a cost-effective and efficient high-resolution construction way based on computational imaging instead of physical imaging from equipment. The image restoration using swin transformer architecture (SwinIR), which leverages the shifted window attention mechanism and dense connections, is introduced to effectively restore fine-grained microstructural details while addressing high noise and complex textures. A Residual Dense Swin Transformer Block (RDSTB) with cross-layer feature fusion is further designed to enhance deep feature reuse and mitigate information degradation in deep networks. Training on diverse cement samples with varying curing ages, water-to-cement ratios, and mix proportions significantly improves the model’s generalization capability. Experimental results demonstrate that the proposed model outperforms existing methods in texture detail recovery and structural fidelity, providing a cost-effective solution for generating high-resolution cement μCT images.

Deep implicit functions (DIFs) effectively represent shapes by using a neural network to map 3D spatial coordinates to scalar values that encode the shape's geometry, but it is difficult to establish correspondences between shapes directly, limiting their use in medical image registration. The recently presented deformation field-based methods achieve implicit templates learning via template field learning with DIFs and deformation field learning, establishing shape correspondence through deformation fields. Although these approaches enable joint learning of shape representation and shape correspondence, the decoupled optimization for template field and deformation field, caused by the absence of deformation annotations lead to a relatively accurate template field but an underoptimized deformation field. In this paper, we propose a novel implicit template learning framework via a shared hybrid diffeomorphic flow (SHDF), which enables shared optimization for deformation and template, contributing to better deformations and shape representation. Specifically, we formulate the signed distance function (SDF, a type of DIFs) as a one-dimensional (1D) integral, unifying dimensions to match the form used in solving ordinary differential equation (ODE) for deformation field learning. Then, SDF in 1D integral form is integrated seamlessly into the deformation field learning. Using a recurrent learning strategy, we frame shape representations and deformations as solving different initial value problems of the same ODE. We also introduce a global smoothness regularization to handle local optima due to limited outside-of-shape data. Experiments on medical datasets show that SHDF outperforms state-of-the-art methods in shape representation and registration.

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 recent years, semi-supervised clustering ensembles have gained significant attention in the field of clustering. These ensembles leverage limited prior knowledge to guide the clustering process. Nonetheless, throughout the integration process, owing to the employment of diverse fundamental clustering algorithms, disparate algorithms generate incongruent results. Consequently, ascertain a more reliable conclusion becomes a formidable challenge. In this paper, we introduce D-CoA (Density based Confidence of Assignment), a novel semi-supervised clustering ensemble algorithm, designed to navigate the intricacies of this issue. D-CoA incorporates sub-clusters using the Minimum Spanning Tree algorithm and evaluates the confidence of each amalgamated cluster to establish prior confidence. Subsequently, a Mixture Density Network is leveraged to calculate the probability density distribution for each merged cluster, yielding posterior confidence scores for resolving conflicts in sample assignments. By adopting this methodology, we amplify the reliability of conflicting sample assignments. Empirical results demonstrate the versatility of this approach, as it effectively accommodates probability distributions of varying shapes, thus demonstrating its feasibility and scalability for diverse data types.

Intrusion detection technology is of great significance to enhance the network security protection of industrial Internet of Things (IIoT) and ensure the efficient implementation of the production process. Aiming at the problems of poor real-time performance and high false positive rate (FPR) of existing intrusion detection methods in IIoT, a sketch-based intrusion detection framework is proposed. The framework employs an improved sketch algorithm as a primary classification module, which is able to process raw traffic in real-time, and perform traffic splitting and filtering efficiently. To improve accuracy, the filtered traffic is fed into a machine learning (ML) based secondary classification module for further analysis. Compared to direct analysis, the sketch can filter out a portion of the benign traffic, thus improving the efficiency of the secondary module. Our framework can work as a pre-module for existing ML based intrusion detection methods, giving them the ability to process traffic in real-time and reduce FPRs. We validate the performance of the framework by testing it on the latest publicly available dataset, Modbus 2023.

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.

Currently, feature selection faces a huge challenge that no single feature selection method can effectively deal with various data sets for all real cases. Ensemble learning is a potential promising solution to address this problem. We propose an ensemble feature selection method based on enhanced co-association matrix (ECM-EFS). Positive-co-association matrix (PCM), negative-co-association matrix (NCM), and relative-co-association matrix (RCM) are first introduced to discover the relationship among features by ensembling the results in multiple feature selection methods. To further produce a more stable feature selection result, “Feature Kernel” is also introduced and used as a starting point for feature selection. Comparative experiments with four state-of-the-art methods have confirmed that the ECM-EFS can provide more robust results. Moreover, compared with traditional ensemble feature selection methods, our method can compensate information loss and reduce computational cost significantly.

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.

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.

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, a reinforced fuzzy radial basis function neural network (R-FRBFNN) classifier is proposed. It focuses on the development of methodologies of reinforced architecture to improve classification accuracy and enhance the robust capability based on two learning strategies. The two learning strategies are summarized: 1) R-FRBFNN designed via support vector (SV)-based fuzzy C-means (FCM) clustering and softmax-based iterative reweighted least square (IRLS), which concentrate on improving the classification performance of R-FRBFNN; and 2) R-FRBFNN designed via SV-based FCM and softmax-based iterative quadratic programming (IQP), which focus on improving the robust abilities of the R-FRBFNN and reducing the effects of noise and outliers. The essential points of the proposed R-FRBFNN classifier are summarized as follows. a) The proposed R-FRBFNN consists of three phases: condition, conclusion, and inference. b) An SV-based FCM is considered for prioritizing the classification boundary and improving the classification performance of the proposed classifier. c) Three types of polynomials construct the conclusion phase. Two learning techniques are designed to update the coefficients of the polynomials. Softmax-based IRLS is a type of iterative learning technique based on Newton's method. Softmax-based IQP is more robust and avoids the degradation of generalization capabilities caused by outliers and noisy data. d) In the concept of reinforced architecture, SV-based FCM imposes compensation (membership degrees) on learning techniques according to the data characteristics encountered in the inference phase. Experimental results reported for benchmark data and outliers/noisy datasets demonstrate that the proposed classifier shows improved classification performance compared with other previously studied methods.

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.

As smartphones carry more and more private information, it has become the main target of malware attacks. Threats on mobile devices have become increasingly sophisticated, making it imperative to develop effective tools that are able to detect and counter such threats. Unfortunately, existing malware detection tools based on machine learning techniques struggle to keep up due to the difficulty in performing online incremental update on the detection models. In this paper, a Two-tier Architecture Malware Detection (TAMD) method is proposed, which can learn from the statistical features of network traffic to detect malware. The first layer of TAMD identifies uncertain samples in the training set through a preliminary classification, whereas the second layer builds an improved classifier by filtering out such samples. We enhance TAMD with an incremental leaning based technique (TAMD-IL), which allows to incrementally update the detection models without retraining it from scratch by removing and adding sub-models in TAMD. We experimentally demonstrate that TAMD outperforms the existing methods with up to 98.72% on precision and 96.57% on recall. We also evaluate TAMD-IL on four concept drift datasets and compare it with classical machine learning algorithms, two state-of-the-art malware detection technologies, and three incremental learning technologies. Experimental results show that TAMD-IL is efficient in terms of both update time and memory usage.

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.

Summary In the mobile computing environment, how to make the data access more efficient is a challenge due to the narrow communication bandwidth, the frequent disconnections of network, and the limited resources. Therefore, it is necessary to cache data on the client side. Besides, a good cache consistency method is essential to ensure the correctness. In this article, a row‐based semantic cache with incremental versioning consistency (RSCVC) is proposed. In RSCVC, we designed a semantic cache algorithm, a query trimming and optimizing algorithm, and a version‐based consistency strategy. This RSCVC cache mainly has two advantages. On one hand, it can obviously improve the response time of query and the hit ratio of the cache. On the other hand, the version‐based consistency enhances the stability of the system especially in high‐concurrency situations. Experiments demonstrate the efficacy of our proposed method and its superiority to state‐of‐the‐art methods.

The detection of 3D interest points is a central problem in computer graphics, computer vision, and pattern recognition. It is also an important preprocessing step in the analysis of 3D model matching. Although studied for decades, detecting 3D interest points remains a challenge. In this study, a novel multiscale bilateral filtering method is presented to detect 3D interest points. This method first simplifies repeatedly the input 3D mesh to form k multiresolution meshes. For each mesh, on the basis of the computed saliency of the mesh vertex, the bilateral filtering is used to remove the noise of the mesh saliencies and the global contrast to normalise the saliencies, and then the interest points are extracted on the basis of the normalised saliency. The proposed method then gathers and clusters all interest points detected on the k multiresolution meshes, and the centres of these clusters are treated as the final interest points. In this method, both the spatial closeness and the geometric similarities of the mesh vertices are considered during the bilateral filtering process. The experimental results validate the effectiveness of the proposed method to detect 3D interest points. This method is also tested the potential to distinguish 3D models.

Network traffic analysis has been widely used for detecting malware at a large-scale network. Nevertheless, the emerging malware variants and zero-day exploits keep posing significant challenges to malware detection systems. In this paper, we propose DART, a framework for detecting malicious network traffic based on Adaptation Regularization Transfer Learning (ARTL), which effectively copes with the unseen malware variants problem. Specifically, DART trains the adaptive classifier by simultaneously optimizing three factors: (i) the structural risk functions; (ii) the joint distribution between the known malware and unseen malware variants domains; and (iii) the manifold consistency underlying marginal distribution. In addition, DART also works with encrypted network traffic since it does not leverage information related to the packet content. We assess the effectiveness and efficiency of our proposal with a thorough set of experiments. DART achieves over 90% F-measure and 91% recall, outperforming conventional traffic classification methods and other state-of-the-art intrusion detection systems.

While more and more antennas are integrated into a single mobile user equipment to increase communication quality and throughput, the number of antennas used for transmission is commonly restricted due to the concerns on hardware complexity and energy consumption, making it impossible to achieve the maximum channel capacity. This paper investigates the problem of reconstructing the full downlink channel from incomplete uplink channel measurements in Massive MIMO systems. We present ARDI, a scheme that builds a bridge between radio channel and physical signal propagation environment to link spatial information about the non-transmitting antennas with their radio channels. By inferring locations and orientations of the non-transmitting antennas from an incomplete set of uplink channels, ARDI can reconstruct the downlink channels for non-transmitting antennas. We derive closed-form solution to reconstruct antenna orientation in both single-path and multipath propagation environments. The performance of ARDI is evaluated using simulations with realistic human movement. The results demonstrate that ARDI is capable of accurately reconstructing full downlink channels when the signal-to-noise ratio is higher than 15dB, thereby expanding the channel capacity of Massive MIMO networks.

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 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.

Summary Live data migration in the cloud is responsible to migrate blocks of data from one emigration node to several immigration nodes. However, live data migration strategy is a NP‐hard problem like task scheduling. Recently, in‐stream processing is a new technique to process large‐scale data nearly instantaneously. This framework works fast that all decisions are made without a continuous stream of events. In this paper, we explore a real‐time live data migration strategy with stream processing paradigm. First, the nonlinear migration cost model and balance model are introduced as the metrics to evaluate the data migration strategy. Subsequently, a live data migration strategy with particle swarm optimization (PSO) is proposed. Two improvement measures called loop context and particle grouping are proposed. As an improvement of stream processing framework, nested loop context structure is a feedback to support iterative optimization algorithm. As an improvement of PSO, grouping particles before in‐stream processing are to speed up the convergence rate of PSO. Afterwards, we rebuild stream processing framework to implement these methods. The experimental results show the best performance of our method.

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.

The emergence of malicious apps poses a serious threat to the Android platform. Most types of mobile malware rely on network interface to coordinate operations, steal users' private information, and launch attack activities. In this paper, we propose an effective and automatic malware detection method using the text semantics of network traffic. In particular, we consider each HTTP flow generated by mobile apps as a text document, which can be processed by natural language processing to extract text-level features. Then, we use the text semantic features of network traffic to develop an effective malware detection model. In an evaluation using 31 706 benign flows and 5258 malicious flows, our method outperforms the existing approaches, and gets an accuracy of 99.15%. We also conduct experiments to verify that the method is effective in detecting newly discovered malware, and requires only a few samples to achieve a good detection result. When the detection model is applied to the real environment to detect unknown applications in the wild, the experimental results show that our method performs significantly better than other popular anti-virus scanners with a detection rate of 54.81%. Our method also reveals certain malware types that can avoid the detection of anti-virus scanners. In addition, we design a detection system on encrypted traffic for bring-your-own-device enterprise network, home network, and 3G/4G mobile network. The detection model is integrated into the system to discover suspicious network behaviors.

Summary Replication is a method to keep the consistency of source data and target data. In our previous work of access‐aware in‐memory data cache middleware for relational databases, the data are easy to be lost in case that power cuts off. Therefore, we investigate a live data replication approach from in‐memory data cache to versioning repository in this paper. This method attempts to recover the in‐memory data cache from the versioning repository in failure of access‐aware in‐memory data cache middleware. Although the replication is not a new problem, the state of art of the replication in the context of document stores is not mature. In our paper, we propose a live data replication approach of in‐memory document stores using stream processing framework. First, we introduce cell state model to describe the replication process. To infinitely look back to any revision, we enable our proposed cell state model to support copy‐modify‐merge model to manage the changed data revisions subsequently. Finally, experimental results show that this approach is more suitable for the replication of continuous in‐stream changed data compared with MapReduce‐based batch replication.

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.

Based on core point evolution using water ripple model, the thought of software development methodology is that the development of a complex system is translated into the water ripple sustainable evolution of core point. However, the core point is defined from three levels, which are domain, feature and function. And it does not give a general definition of the core point. In addition, the evolution of the core point only gives a simple evolutionary model, and there is no evolutionary algorithm between the core points. To address these problems, this paper further improves the feature and function core points, and put forward the framework and level core points. Then, this paper also give the corresponding evolutionary algorithm. Based on these two points, this paper developed a prototype system in order to demonstrate the water ripple evolution of the various types of core points.

Android has become the most popular mobile platform due to its openness and flexibility. Meanwhile, it has also become the main target of massive mobile malware. This phenomenon drives a pressing need for malware detection. In this paper, we propose TrafficAV, which is an effective and explainable detection of mobile malware behavior using network traffic. Network traffic generated by mobile app is mirrored from the wireless access point to the server for data analysis. All data analysis and malware detection are performed on the server side, which consumes minimum resources on mobile devices without affecting the user experience. Due to the difficulty in identifying disparate malicious behaviors of malware from the network traffic, TrafficAV performs a multi-level network traffic analysis, gathering as many features of network traffic as necessary. The proposed method combines network traffic analysis with machine learning algorithm (C4.5 decision tree) that is capable of identifying Android malware with high accuracy. In an evaluation with 8,312 benign apps and 5,560 malware samples, TCP flow detection model and HTTP detection model all perform well and achieve detection rates of 98.16% and 99.65%, respectively. In addition, for the benefit of user, TrafficAV not only displays the final detection results, but also analyzes the behind-the-curtain reason of malicious results. This allows users to further investigate each feature's contribution in the final result, and to grasp the insights behind the final decision.

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.

Data deduplication is the task of identifying all groups of objects within one or several data sets, respectively. However, this task will become difficult in the context of big data. To address this limitation, we propose a new schema-free data deduplication approach in parallel in the aspect of breeding data deduplication related to food safety. Although MapReduce framework enables efficient parallel execution of data-intensive tasks, it cannot find duplicates in adjacent block. Furthermore, current deduplication approaches with MapReduce are restricted to fixed sliding window. Therefore, we investigate possible solutions to improve current deduplication approaches with MapReduce, to make sliding window size adaptive using adaptive multiple duplicate count strategy with alterable window step, and find duplicates by overlapping boundary objects in adjacent blocks. Moreover, we propose a multi-pass Partition-Sort-Map-Reduce approach with adaptive sliding window to speed up the deduplication process. Finally, our experimental evaluation based on the breeding data on large datasets shows the high effectiveness and efficiency of the proposed approaches.

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.

Currently, full-text searching can benefit from the emerging NoSQL databases and traditional indexing tools in the big data era. However, there are some drawbacks of current solutions. On one hand, the indexing documents lack of the hierarchy. On the other hand, big data have become the bottleneck of full-text searching. In the context of big data, we design a full-text searching middleware over hierarchical documents. We discuss the architecture of this middleware in detail. In addition, we propose a structure-independent hierarchical document model to present the hierarchical document. Moreover, the transformation engine is designed to translate the rich files into models. The core log event listener is responsible for capturing the changed documents and push them to the indexing storage at the same time. The experimental results show that our middleware is more advantageous than RDBMS with indexes and RDBMS with Lucene solutions.

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.

Model transformation plays an important role in current MDD (Model Driven Development). Combined with direct model manipulation, relational algebra and template theory, this paper presents a formalizing hybrid model transformation for the design in universal collaborative system. Furthermore, it implements an extendible prototype system based on MDA paradigm called CSCWMDA. CSCWMDA specifies a model driven process that takes UML models and generates collaborative system code by hybrid model transformation. Finally, a case study of Cooperative Authoring System illustrates our approach demonstrating the hybrid MDE process. This approach removes the heterogeneity of model transformation to some extent, and at the same time it is simple and well regulated.

Traditional traffic classification techniques like port-based and payload-based techniques are becoming ineffective owning to more and more Internet applications using dynamic port number and encryption techniques. Therefore, in the past few years, many researches have addressed machine learning-based techniques. Most researches of machine learning-based traffic identification use traffic samples collected on key nodes of networks for their learning. These samples do not have accurate application information i. e. the ground truth which is crucial for machine learning algorithms. In this paper, we first designed a distributed host based traffic collecting platform (DHTCP) to gather traffic samples with accurate application information on user hosts. Then we built a data set using DHTCP, and applied Flexible Neural Trees (FNT) - a special kind of artificial neural network which has been successfully applied in many areas, for traffic identification. Web and P2P traffics were studied in our work. Although the proposed technique is at an early stage of development, experimental results show that it is a promising solution of Internet traffic identification.

An intrusion is defined as a violation of the security policy of the system, and, hence, intrusion detection mainly refers to the mechanisms that are developed to detect violations of system security policy. Current intrusion detection systems (IDS) examine all data features to detect intrusion or misuse patterns. Some of the features may be redundant or contribute little (if anything) to the detection process. The purpose of this study is to identify important input features in building an IDS that is computationally efficient and effective. This article proposes an IDS model based on a general and enhanced flexible neural tree (FNT). Based on the predefined instruction/operator sets, a flexible neural tree model can be created and evolved. This framework allows input variables selection, overlayer connections, and different activation functions for the various nodes involved. The FNT structure is developed using an evolutionary algorithm, and the parameters are optimized by a particle swarm optimization algorithm. Empirical results indicate that the proposed method is efficient. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 337–352, 2007.

This paper presents an automatic way of evolving hierarchical Takagi-Sugeno fuzzy systems (TS-FS). The hierarchical structure is evolved using probabilistic incremental program evolution (PIPE) with specific instructions. The fine tuning of the if - then rule's parameters encoded in the structure is accomplished using evolutionary programming (EP). The proposed method interleaves both PIPE and EP optimizations. Starting with random structures and rules' parameters, it first tries to improve the hierarchical structure and then as soon as an improved structure is found, it further fine tunes the rules' parameters. It then goes back to improve the structure and the rules' parameters. This loop continues until a satisfactory solution (hierarchical TS-FS model) is found or a time limit is reached. The proposed hierarchical TS-FS is evaluated using some well known benchmark applications namely identification of nonlinear systems, prediction of the Mackey-Glass chaotic time-series and some classification problems. When compared to other neural networks and fuzzy systems, the developed hierarchical TS-FS exhibits competing results with high accuracy and smaller size of hierarchical architecture.

Technology trends in today's cooperative design environments are making it more and more important to monitor the network performance and ensure the network security. This paper describes the design and implementation of a distributed network traffic monitoring system based on embedded NetFlow hardware and software engines. The system architecture and design principles were introduced in the paper, some discussions were also presented about the NetFlow-based network monitoring technologies. The system had been successfully used to monitor highspeed campus networks at full wire speed without packet sampling in scenarios where commercial NetFlow collectors could not be used due to their limitations. Results show that this is an effective mechanism to identify, diagnose, and determine controls for network activities in CSCW environments and other network-based applications.

This paper introduces a flexible neural tree model. The model is computed as a flexible multi-layer feed-forward neural network. A hybrid learning/evolutionary approach to automatically optimize the neural tree model is also proposed. The approach includes a modified probabilistic incremental program evolution algorithm (MPIPE) to evolve and determine a optimal structure of the neural tree and a parameter learning algorithm to optimize the free parameters embedded in the neural tree. The performance and effectiveness of the proposed method are evaluated using function approximation, time series prediction and system identification problems and compared with the related methods.