Search

Deep learning is widely used in Bearing Fault Diagnosis (BFD). Nonetheless, practical industrial production often generates a large amount of industrial noise. These noises exhibit randomness and complexity, which puts forward higher requirements for diagnosis algorithms. Certain studies have tackled the issue of anti-interference in high-noise environments (S N R ≤ 0 dB) by increasing the complexity of the model. However, due to the excessive number of parameters and computation, such models cannot be deployed on low-end edge devices. Balancing resource consumption and accuracy has become a major challenge in BFD modeling research. To solve the above problems, this paper proposes a new Transformer architecture model called LTFAFormer. The LTFAFormer is capable of achieving high-precision diagnostics on low-end edge devices and shows greater noise resistance. In terms of processing sequence information, Transformer has proven to be superior to other solutions. However, when dealing with longer sensor signal data containing complex noise, the traditional self-attention mechanism not only cannot effectively extract fault features, but also generates more computational complexity than CNN. To address this issue, we propose a novel time–frequency dual-channel parallel attention mechanism. Our approach enhances the feature extraction capability of the model by expanding the attention computation scale and reduces the computational resource consumption of the model by optimizing the model structure. To validate the effectiveness of LTFAFormer, we present two cases to demonstrate that LTFAFormer has higher prediction accuracy while satisfying lightweight. Especially in high-noise environments, LTFAFormer has stronger robustness. In this paper provides a new set of feasible strategies for the practical deployment of BFD models in practical industrial environments. • The LTFAFormer, a lightweight and noise-robust model, is ideal for low-end devices. • Added a Dual-Channel Attention Module to expand traditional self-attention scale. • Developed a Cross-fusion mechanism for attention to enhance feature fusion. • Optimized the model's embedding module based on sensor signal traits. • Our model outperforms others in bearing fault diagnosis and is robust in noise. [Display omitted] [ABSTRACT FROM AUTHOR]

In order to solve the problem that the Transformer model cannot apply to mobile devices with limited computational resources due to its huge number of parameters and computational complexity, this paper proposed a mobile-friendly lightweight image recognition network called FuseNet. FuseNet utilized convolutional neural network to extract local feature information and self-attention to excel in modeling global information, and it integrated the features of both local and global representations into a single feature extraction module, which efficiently combined the advantages of the two different structures to achieve a high accuracy with a small model size. Experiments demonstrate that FuseNet with different model sizes can achieve good performance without using pre-training and it can well apply to mobile devices. FuseNet-B achieves 80. 5% accuracy with 14. 8 M parameters on ImageNet-1 K dataset, the performance exceeds the same volume of Transformer models and convolutional neural networks. [ABSTRACT FROM AUTHOR]

Most of the eye disease classification methods are to classify a single category of diseases at different levels, and the network model has problems such as large parameters and complex calculations. To solve these problems, this paper proposed a lightweight fundus disease multi-classification network called MELCNet. The network used PPLCNet as the backbone, which was composed of input layer for feature extraction, parallel multi-scale structure, bilinear SE attention module, depth separable convolution and the h-swish activation function which calculated with smaller parameters, in order to pay attention to the key disease information of different scales and different diseases. Experimental results show that the proposed multi-scale attention lightweight network model has less parameters and computational complexity, and excellent classification results have been obtained in the multi-classification of the four selected fundus diseases and normal fundus images. The classification accuracy in the internal combined test set is 1.11 % higher than that in ResNet-50,and the performance on the public datasets is improved by 2. 5% relative to the multi-classification literature of similar type network by Xie et al, and compared with other lightweight classification networks, it has higher accuracy and strong robustness in the field of multi-classification of fund us diseases. [ABSTRACT FROM AUTHOR]

To solve the problem of category-oriented 3D articulated objects pose estimation, this paper proposed a category-oriented 3D object pose estimation method based on key points. It designed a network based on key points, which used PointNet + + as base network and estimated the pose of the object through feature extraction, key points extraction, and pose prediction with high accuracy and robust. At the same time, based on ANCSH, it proposed a hierarchical standardized category representation method of key points for K-AOPE, which only required a few points to describe the object category. To evaluate the method, it did some experiments on the public motion dataset shape2motion. The results show that the rotation angle errors of the proposed method are 2. 3°, 3. 1°, 3. 7°, the translation errors are 0. 034, 0. 030, 0. 046, the joint state error are 2. 4°, 2. 5°, and the joint parameter error are 1. 2°, 0. 9°, 0. 008, 0. 010. Compared with other similar methods, the proposed method has lower computational complexity and higher robust. [ABSTRACT FROM AUTHOR]

Highlights • Grasshopper optimization algorithm is used to propose a feature selection method. • Computation of feature goodness factor helps to find global solution. • The accuracy of 100% is achieved by selecting 4 features out of 2308 in a dataset. • The method achieves the highest classification accuracy in 7 out of 10 datasets. Abstract Feature selection is the problem of finding the minimum number of features among a redundant feature space which leads to the maximum classification performance. In this paper, we have proposed a novel feature selection method based on mathematical model of interaction between grasshoppers in finding food sources. Some modifications were applied to the grasshopper optimization algorithm (GOA) to make it suitable for a feature selection problem. The method, abbreviated as GOFS is supplemented by statistical measures during iterations to replace the duplicate features with the most promising features. Several publicly available datasets with various dimensionalities, number of instances, and target classes were considered to evaluate the performance of the GOFS algorithm. The results of implementing twelve well-known and recent feature selection methods were presented and compared with GOFS algorithm. Comparative experiments indicate the significance of the proposed method in comparison with other feature selection methods. [ABSTRACT FROM AUTHOR]

Case-based planning can fruitfully exploit knowledge gained by solving a large number of problems, storing the corresponding solutions in a plan library and reusing them for solving similar planning problems in the future. Case-based planning is very effective when similar reuse candidates can be efficiently and effectively chosen. In this paper, we study an innovative technique based on planning problem features for efficiently retrieving solved planning problems (and relative plans) from large plan libraries. A problem feature is a characteristic -usually provided under the form of a number- of the instance that can be automatically derived from the problem specification, domain and search space analyses, or different problem encodings. Given a planning problem to solve, its features are extracted and compared to those of problems stored in the case base, in order to identify most similar problems. Since the use of existing planning features is not always able to effectively distinguish between problems within the same planning domain, we introduce a large number of new features. An experimental analysis in this paper investigates the best set of features to be exploited for retrieving plans in case-based planning, and shows that our feature-based retrieval approach can significantly improve the performance of a state-of-the-art case-based planning system. [ABSTRACT FROM AUTHOR]

It is well-known that ensemble of classifiers can achieve higher accuracy compared to a single classifier system. This paper pays attention to ensemble systems consisting of multiple feature extractors and multiple classifiers (MFMC). However, MFMC increases the system complexity dramatically, leading to a highly complex combinatorial optimization problem. In order to overcome the complexity while exploiting the diversity of MFMC, we suggest in this paper a hierarchical ensemble of MFMC and its optimizing framework. By constructing local groups of feature extractors and classifiers and then combining them as a global group, the approach achieves a better scalability. Both reinforcement machine learning and Bayesian networks are adopted to enhance the accuracy. We apply the proposed method to vision based pedestrian detection and recognition of handwritten numerals. Experimental results show that the proposed framework outperforms the previous ensemble methods in terms of accuracy. [ABSTRACT FROM AUTHOR]

• A multiview method, GRMDA, is proposed for extracting the robust and sparse features, which reconstructs within-class scatter term and between-class scatter term in multiview scenario using L 2 , 1 norm to enhance robustness. • We conduct the analysis of small-class problem and adopt another criterion inspired by MMC to solve this problem. In terms of overfitting problem, the L 2 , 1 norm is also imposed on the regularization term for extracting sparse features. • The paper presents an iterative algorithm to compute optimal linear transform for each view. The poof of convergence is provided, and the computational complexity is analyzed. Several experiments were conducted to evaluate the performance of GRMDA Multiview data leads to the demand for classifying samples from various views, and the large gap between different views makes the classification task challenging. Recently, researchers have extended linear discriminant analysis (LDA) to multi-view scenarios. However, the extended methods are generally associated with the small-class problem, that is, the projection size is limited by the number of classes. In addition, they are sensitive to variations in images or outliers. To solve these problems, this study proposes a generalized robust multiview discriminant analysis (GRMDA) to obtain a linear transform for each view and for learning multiview jointly sparse discriminant common subspace. GRMDA aims to achieve both maximal between-class and minimal within-class variation for data from multiple views in a common space. Instead of formulating the ratio trace problem, we reformulate GRMDA inspired by maximum margin criterion (MMC) to address the small-class problem. Moreover, the proposed method achieves stronger robustness by reconstructing the within-class and between-class scatter terms from the definition of L 2 , 1 norm. Furthermore, GRMDA ensures joint sparsity using the L 2 , 1 norm-based regularization term. Additionally, we present an iterative algorithm, convergence proof, and complexity analysis. Experiments on six popular databases, that is, COIL100, USPS/MNIST, Extended Yale Face B, AR, BBCSport, and multiple feature datasets, were conducted to evaluate the performance of GRMDA against the state-of-the-art multiview methods. The experimental results demonstrate that the proposed method can achieve a significant performance with strong robustness and fast convergence. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, an adequate set of input features is selected for functional expansion genetically for the purpose of solving the problem of classification in data mining using functional link neural network. The proposed method named as HFLNN aims to choose an optimal subset of input features by eliminating features with little or no predictive information and designs a more compact classifier. With an adequate set of basis functions, HFLNN overcomes the non-linearity of problems, which is a common phenomenon in single layer neural networks. The properties like simplicity of the architecture (i.e., no hidden layer) and the low computational complexity of the network (i.e., less number of weights to be learned) encourage us to use it in classification task of data mining. We present a mathematical analysis of the stability and convergence of the proposed method. Further the issue of statistical tests for comparison of algorithms on multiple datasets, which is even more essential in data mining studies, has been all but ignored. In this paper, we recommend a set of simple, yet safe, robust and non-parametric tests for statistical comparisons of the HFLNN with functional link neural network (FLNN) and radial basis function network (RBFN) classifiers over multiple datasets by an extensive set of simulation studies. [Copyright &y& Elsevier]

Stream runtime verification ( SRV ), pioneered by the tool LOLA, is a declarative formalism to specify synchronous monitors. In SRV , monitors are described by specifying dependencies between output streams of values and input streams of values. The declarative nature of SRV enables a separation between the evaluation algorithms, and the monitor storage and its individual updates. This separation allows SRV to be lifted from conventional failure monitors into richer domains to collect statistics of traces. Moreover, SRV allows to easily identify specifications that can be efficiently monitored online, and to generate efficient schedules for offline monitors. In spite of these attractive features, many important theoretical problems about SRV are still open. In this paper, we address complexity, expressiveness, succinctness, and closure issues for the subclass of Boolean SRV ( BSRV ) specifications. Additionally, we show that for this subclass, offline monitoring can be performed with only two passes (one forward and one backward) over the input trace in spite of the alternation of past and future references in the BSRV specification. [ABSTRACT FROM AUTHOR]

Real time pedestrian tracking could be one of the important features for autonomous navigation. Laser Range Finder (LRF) produces accurate pedestrian data but a problem occurs when a pedestrian is represented by multiple clusters which affect the overall tracking process. Multiple Hypothesis Tracking (MHT) is a proven method to solve tracking problem but suffers a large computational cost. In this paper, a multilevel clustering of LRF data is proposed to improve the accuracy of a tracking system by adding another clustering level after the feature extraction process. A Dynamic Track Management (DTM) is introduced in MHT with multiple motion models to perform a track creation, association, and deletion. The experimental results from real time implementation prove that the proposed multiclustering is capable of producing a better performance with less computational complexity for a track management process. The proposed Dynamic Track Management is able to solve the tracking problem with lower computation time when dealing with occlusion, crossed track, and track deletion. [ABSTRACT FROM AUTHOR]

The self-organizing map (SOM) is a traditional neural network algorithm used to achieve feature extraction, clustering, visualization and data exploration. However, it is known that the computational cost of the traditional SOM, used to search for the winner neuron, is expensive especially in case of treating high-dimensional data. In this paper, we propose a novel hierarchical SOM search algorithm which significantly reduces the expensive computational cost associated with traditional SOM. It is shown here that the computational cost of the proposed approach, compared to traditional SOM, to search for the winner neuron is reduced into O(D1 + D2 + ⋯ + DN) instead of O(D1 × D2 × ⋯ × DN), where Dj is the number of neurons through a dimension dj of the feature map. At the same time, the new algorithm maintains all merits and qualities of the traditional SOM. Experimental results show that the proposed algorithm is a good alternate to traditional SOM, especially, in high-dimensional feature space problems. [ABSTRACT FROM AUTHOR]

Semi-supervised multi-view learning methods aim to boost the learning performance by conjunction with labeled data, because the label information can enhance the discriminant ability of the learned model. Recently, non-negative matrix factorization has received widespread attention in semi-supervised multi-view learning due to its powerful ability of feature extraction. However, the problem of very limited available labeled data is seldom considered. In this case, it is hard for existing approaches to obtain satisfied performance. Motivated by that the label propagation can classify a large number of unlabeled data with few labeled data, in this paper, we propose a novel semi-supervised multi-view learning approach to address the problem of sparse labeled data, called Label Propagation based Non-negative Matrix Factorization (LPNMF). In our model, the intrinsic manifold structure of data is constructed by the adaptive neighbors technology. Based on this intrinsic manifold structure, the label propagation is further employed to make full use of the limited labeled data. Besides, we design an efficient alternating algorithm for solving the optimization problem and provide theoretical analysis on its convergence properties and computational complexity. Finally, experiments on four real-world datasets demonstrate the advantage of our proposed methods, with comparison to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep learning models have strong abilities in learning features and they have been successfully applied in hyperspectral images (HSIs). However, the training of most deep learning models requires labeled samples and the collection of labeled samples are labor-consuming in HSI. In addition, single-level features from a single layer are usually considered, which may result in the loss of some important information. Using multiple networks to obtain multi-level features is a solution, but at the cost of longer training time and computational complexity. To solve these problems, a novel unsupervised multi-level feature extraction framework that is based on a three dimensional convolutional autoencoder (3D-CAE) is proposed in this paper. The designed 3D-CAE is stacked by fully 3D convolutional layers and 3D deconvolutional layers, which allows for the spectral-spatial information of targets to be mined simultaneously. Besides, the 3D-CAE can be trained in an unsupervised way without involving labeled samples. Moreover, the multi-level features are directly obtained from the encoded layers with different scales and resolutions, which is more efficient than using multiple networks to get them. The effectiveness of the proposed multi-level features is verified on two hyperspectral data sets. The results demonstrate that the proposed method has great promise in unsupervised feature learning and can help us to further improve the hyperspectral classification when compared with single-level features. [ABSTRACT FROM AUTHOR]

The rapid growth of fingerprint authentication-based applications makes presentation attack detection, which is the detection of fake fingerprints, become a crucial problem. There have been numerous attempts to deal with this problem; however, the existing algorithms have a significant trade-off between accuracy and computational complexity. This paper proposes a presentation attack detection method using Convolutional Neural Networks (CNN), named fPADnet (fingerprint Presentation Attack Detection network), which consists of Fire and Gram-K modules. Fire modules of fPADnet are designed following the structure of the SqueezeNet Fire module. Gram-K modules, which are derived from the Gram matrix, are used to extract texture information since texture can provide useful features in distinguishing between real and fake fingerprints. Combining Fire and Gram-K modules results in a compact and efficient network for fake fingerprint detection. Experimental results on three public databases, including LivDet 2011, 2013 and 2015, show that fPADnet can achieve an average detection error rate of 2.61%, which is comparable to the state-of-the-art accuracy, while the network size and processing time are significantly reduced. [ABSTRACT FROM AUTHOR]