Search

In the practical application of high-frequency surface wave radar (HFSWR), ionospheric clutter has become the principal obstacle to target detection. Since ionospheric clutter has nonlinear and time-varying characteristics, the current suppression methods still require improvement. In this letter, we proposed a method merging the deep neural networks (DNNs) and linear Koopman operator from the dynamic perspective, combining the powerful learning capacity of neural networks and the interpretability of Koopman theory, and applied linear Koopman mode to represent nonlinear ionospheric clutter in the state space based on time-delayed coordinates to achieve the finite-dimensional linear approximate reconstruction of ionospheric clutter. The validation results of the measured data reveal that the method has satisfactory modeling accuracy, which proves the effectiveness of the approach and lays the foundations for the subsequent breakthrough in new methods for ionospheric clutter suppression. [ABSTRACT FROM AUTHOR]

In this article, the structure and motion of a moving object are asymptotically estimated by an uncalibrated vehicle-mounted two-camera system under uneven road condition. Concurrent learning techniques are utilized to compensate for the cameras’ extrinsic parameters, and a time-varying gain is introduced to accelerate the estimation. Meanwhile, geometric relationships are used along with the visual information to obtain depth and 3-D coordinates of a feature point located on the moving object. Homography techniques are utilized to construct a measurable auxiliary state whose dynamics is related to the moving point’s velocity, which is further obtained by a nonlinear observer. Lyapunov-based analysis is conducted to prove the asymptotic convergence of the cameras’ extrinsic parameters as well as the moving point’s depth and velocity. The proposed method is applicable for different sensor configurations and road conditions as long as proper linear parameterization is done for the vision-based dynamics. Both simulations and experiments are conducted to verify the effectiveness and performance of the proposed method. [ABSTRACT FROM AUTHOR]

Linear discriminant analysis (LDA) has been proven to be effective in dimensionality reduction. However, the performance of LDA depends on the consistency assumption of the global structure and the local structure. Some work extended LDA along this line of research and proposed local formulations of LDA. Unfortunately, the learning scheme of these algorithms is suboptimal in that the intrinsic relationship between data points is pre-learned in the original space, which is usually affected by the noise and redundant features. Besides, the time cost is relatively high. To alleviate these drawbacks, we propose a Fast Locality Discriminant Analysis framework (FLDA), which has three advantages: (1) It can divide a non-Gaussian distribution class into many sub-blocks that obey Gaussian distributions by using the anchor-based strategy. (2) It captures the manifold structure of data by learning the fuzzy membership relationship between data points and the corresponding anchor points, which can reduce computation time. (3) The weights between data points and anchor points are adaptively updated in the subspace where the irrelevant information and the noise in high-dimensional space have been effectively suppressed. Extensive experiments on toy data sets, UCI benchmark data sets and imbalanced data sets demonstrate the efficiency and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The berth allocation problem (BAP) is an NP-hard problem in maritime traffic scheduling that significantly influences the operational efficiency of the container terminal. This paper formulates the BAP as a permutation-based combinatorial optimization problem and proposes an improved ant colony system (ACS) algorithm to solve it. The proposed ACS has three main contributions. First, an adaptive heuristic information (AHI) mechanism is proposed to help ACS handle the discrete and real-time difficulties of BAP. Second, to relieve the computational burden, a divide-and-conquer strategy based on variable-range receding horizon control (vRHC) is designed to divide the complete BAP into a set of sub-BAPs. Third, a partial solution memory (PSM) mechanism is proposed to accelerate the ACS convergence process in each receding horizon (i.e., each sub-BAP). The proposed algorithm is termed as adaptive ACS (AACS) with vRHC strategy and PSM mechanism. The performance of the AACS is comprehensively tested on a set of test cases with different scales. Experimental results show that the effectiveness and robustness of AACS are generally better than the compared state-of-the-art algorithms, including the well-performing adaptive evolutionary algorithm and ant colony optimization algorithm. Moreover, comprehensive investigations are conducted to evaluate the influences of the AHI mechanism, the vRHC strategy, and the PSM mechanism on the performance of the AACS algorithm. [ABSTRACT FROM AUTHOR]

Semi-supervised learning as one of most attractive problems in machine learning research field has aroused broad attentions in recent years. In this paper, we propose a novel locality preserved dimensionality reduction framework, named Semi-supervised Adaptive Local Embedding learning (SALE), which learns a local discriminative embedding by constructing a $k_1$ k 1 Nearest Neighbors ($k_1$ k 1 NN) graph on labeled data, so as to explore the intrinsic structure, i.e., sub-manifolds from non-Gaussian labeled data. Then, mapping all samples into learned embedding and constructing another $k_2$ k 2 NN graph on all embedded data to explore the global structure of all samples. Therefore, the unlabeled data and their corresponding labeled neighbors can be clustered into same sub-manifold, so as to improve the discriminative power of embedded data. Furthermore, we propose two semi-supervised dimensionality reduction methods with orthogonal and whitening constraints based on proposed SALE framework. An efficient alternatively iterative optimization algorithm is developed to solve the NP-hard problem in our models. Extensive experiments conducted on several synthetic and real-world data sets demonstrate the superiorities of our methods on local structure exploration and classification task. [ABSTRACT FROM AUTHOR]

Fuzzy $c$ -means method (FCM) is a popular clustering method, which uses alternating iteration algorithm to update membership matrix $\mathbf {F}$ and center matrix $\mathbf {M}$ of $d \times c$ size. However, original FCM suffers from finding a suboptimal local minimum, which limits the performance of FCM. In this article, we propose a new optimization method for fuzzy $c$ -means problem. We first propose an equivalent minimization problem of FCM, then, a simple alternating iteration algorithm is proposed to solve the new minimization problem, which involves an effective and theoretically guaranteed Iteratively Reweighted (IRW) method, so we call the new optimization method IRW-FCM. Our IRW-FCM utilizes $c$ not $dc$ intermediate variables to update $\mathbf {F}$ , which can decrease space complexity. Extensive experiments including objective-function value comparison and clustering-performance comparison show that IRW-FCM can obtain better local minima than FCM with fewer iterations. And according to the time-complexity analysis, it is verified IRW-FCM has the same linear time complexity with FCM. What's more, compared with other clustering methods, IRW-FCM also shows its superiority. [ABSTRACT FROM AUTHOR]

This paper provides an adaptive hybrid robust filter (AHRF) for multi-sensor relative navigation systems that can be used to support cooperative intelligent transport systems. It is known that Huber’s M-estimation based robust filter and the fault detection and exclusion (FDE) based RAIM filter each has its own drawbacks, depending on the nature of the observation error biases. Based on the interactive multiple model (IMM) framework, our proposed AHRF in this paper can take advantage of both filters in a complementary sense. A new adaptive IMM (AIMM) algorithm with Markov transition probability prediction is proposed to allow AHRF to switch efficiently between the two filters. We consider the relative navigation system with Global Navigation Satellite System (GNSS) and ultra-wideband (UWB) as observations to verify AHRF in three cases of possible failure modes and multipath-induced errors. Our results show that AHRF outperforms both the FDE and robust filter in all cases. AHRF framework can be further adapted to include many other fault-tolerant filters to improve the robustness of multi-sensor relative navigation system even further. [ABSTRACT FROM AUTHOR]

Linear Discriminant Analysis (LDA) has been widely used in supervised dimensionality reduction fields. However, LDA is usually weak in tackling data with Non-Gaussian distribution due to its incapability of extracting the intrinsic structure of data. In order to learn the intrinsic information more effectively, some dimensionality reduction methods incorporate the adaptive full-connected graph into the algorithm frame, but the defect is that the calculation of each pairwise distance is very time-consuming. In this letter, we propose a novel fast adaptive local subspace learning with regressive regularization model to solve the supervised dimensional reduction problem. Firstly, the adaptive anchor point graph is used to capture local structure information, which can greatly reduce computation complexity. Secondly, by using regressive regularization, the samples from different classes can be better separated in the projected space and the workload of selecting the optimal reduced dimension is easier. Moreover, entropy regularization is used to derive more appropriate weights. Finally, extensive experiments are conducted on real world data sets to verify the superiority of our model. [ABSTRACT FROM AUTHOR]

The multiple kernel $k$ -means (MKKM) and its variants utilize complementary information from different sources, achieving better performance than kernel $k$ -means (KKM). However, the optimization procedures of most previous works comprise two stages, learning the continuous relaxation matrix and obtaining the discrete one by extra discretization procedures. Such a two-stage strategy gives rise to a mismatched problem and severe information loss. Even worse, most existing MKKM methods overlook the correlation among prespecified kernels, which leads to the fusion of mutually redundant kernels and bad effects on the diversity of information sources, finally resulting in unsatisfying results. To address these issues, we elaborate a novel Discrete and Parameter-free Multiple Kernel $k$ -means (DPMKKM) model solved by an alternative optimization method, which can directly obtain the cluster assignment results without subsequent discretization procedure. Moreover, DPMKKM can measure the correlation among kernels by implicitly introducing a regularization term, which is able to enhance kernel fusion by reducing redundancy and improving diversity. Noteworthily, the time complexity of optimization algorithm is successfully reduced, through masterly utilizing of coordinate descent technique, which contributes to higher algorithm efficiency and broader applications. What’s more, our proposed model is parameter-free avoiding intractable hyperparameter tuning, which makes it feasible in practical applications. Lastly, extensive experiments conducted on a number of real-world datasets illustrated the effectiveness and superiority of the proposed DPMKKM model. [ABSTRACT FROM AUTHOR]

Fuzzy clustering is one of the most popular clustering approaches and has attracted considerable attention in many fields. However, high computational cost has become a bottleneck which limits its applications in large-scale problems. Moreover, most fuzzy clustering algorithms are sensitive to noise. To address these issues, a novel fuzzy clustering algorithm, called fast fuzzy clustering based on anchor graph (FFCAG), is proposed. The FFCAG algorithm integrates anchor-based similarity graph construction and membership matrix learning into a unified framework, such that the prior knowledge of anchors can be further utilized to improve clustering performance. Specifically, FFCAG first constructs an anchor-based similarity graph with a parameter-free neighbor assignment strategy. Then, it designs a quadratic programming model to learn the membership matrix of anchors, which is very different from traditional fuzzy clustering algorithms. More importantly, a novel balanced regularization term is introduced into the objective function to produce more accurate clustering results. Finally, we adopt an alternating optimization algorithm with guaranteed convergence to solve the proposed method. Experimental results performed on synthetic and real-world datasets demonstrate the proposed FFCAG can significantly reduce the computational time with comparable, even superior, clustering performance, compared with state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

In this article, we propose a novel feature selection approach via explicitly addressing the long-standing subspace sparsity issue. Leveraging $\ell _{2,1}$ -norm regularization for feature selection is the major strategy in existing methods, which, however, confronts sparsity limitation and parameter-tuning trouble. To circumvent this problem, employing the $\ell _{2,0}$ -norm constraint to improve the sparsity of the model has gained more attention recently whereas, optimizing the subspace sparsity constraint is still an unsolved problem, which only can acquire an approximate solution and without convergence proof. To address the above challenges, we innovatively propose a novel subspace sparsity discriminative feature selection (S2DFS) method which leverages a subspace sparsity constraint to avoid tuning parameters. In addition, the trace ratio formulated objective function extremely ensures the discriminability of selected features. Most important, an efficient iterative optimization algorithm is presented to explicitly solve the proposed problem with a closed-form solution and strict convergence proof. To the best of our knowledge, such an optimization algorithm of solving the subspace sparsity issue is first proposed in this article, and a general formulation of the optimization algorithm is provided for improving the extensibility and portability of our method. Extensive experiments conducted on several high-dimensional text and image datasets demonstrate that the proposed method outperforms related state-of-the-art methods in pattern classification and image retrieval tasks. [ABSTRACT FROM AUTHOR]

In the application on sleeping heart monitoring by using capacitive electrocardiogram (cECG), a raw cECG signal with high quality is usually difficult to be obtained due to the low coupling capacitance composed of human skin, pajamas, bed sheet and sensing electrodes. This is mainly caused by a low relative dielectric constant of bed sheet and pajamas. In order to overcome this challenge, this study proposed a cECG system containing hydrogel-textile electrode for sleeping heart monitoring. The hydrogel layer was applied in an array pattern onto conductive textile to become a sensitive electrode in order to increase the coupling capacitance and lower the equivalent impedance as well, which was helpful to improve the quality of raw cECG signals. The reference electrode was linked to the circuit of the signal acquisition circuit to decrease the common-mode noises. The system incorporates eight membrane pressure sensors to capture the body’s sleep postures and detect the cECG signals from different sleep postures. The experimental results on tests with three different human sleep postures showed that the signal-noise ratio of the proposed system was close to the wet-electrode based ECG system. The sleeping heart monitoring experiments were conducted involving eight subjects with no constraint conditions through a period of two hours, the R-wave of the cECG signal was analyzed using RR interval extraction algorithms and the heart rate (HR) was calculated. The results showed that all subjects’ HRs during sleep state falls into a normal range, indicating that no signs of tachycardia and bradycardia can be observed. [ABSTRACT FROM AUTHOR]