Adaptive Weight Vector Research Articles

Adaptive decomposition-based evolutionary algorithm for many-objective optimization with two-stage dual-density judgment

In order to better balance the convergence and diversity of MOEA/D for many objective optimization problems (MaOPs) with various Pareto fronts (PFs), an adaptive decomposition-based evolutionary algorithm for MaOPs with two-stage dual-density judgment is proposed. To solve the problem that weighted Tchebycheff decomposition may produce weakly Pareto optimal solutions when the solution is not unique or the uniqueness is difficult to guarantee, an augmented weighted Tchebycheff decomposition is adopted. To balance the convergence and diversity of non-dominated solutions in the external archive, different sparsity-level evaluations using vector angles or Euclidean distances are used to measure the distribution of solutions at different stages. To improve the diversity of solution sets obtained by MOEA/D for various PFs, an adaptive weight vector adjustment method based on two-stage dual-density judgment is presented. For weight vector addition, the potential search area is found according to the two-stage density judgment, and then a two-stage sparsity level judgment on the solutions of this area is performed for a second density judgment. For weight vector deletion, the degree of crowding is used to delete the weight vectors with a high crowding degree. Compared with nine advanced multi-objective optimization algorithms on DTLZ and WFG problems, the results demonstrate that the performance of the proposed algorithm is significantly better than other algorithms.

A linearly constrained framework for the analysis of the deficient length least-mean square algorithm

Most adaptive system identification analyses assume the length of the adaptive filter to match the length of the unknown system response. This assumption tends to be unrealistic, and its conclusions may not apply to some practical applications. The behavior of deficient length adaptive filters has been studied using different approaches. This work formulates the deficient length adaptive system problem using a Linearly Constrained Minimum Mean Squared Error (LCMMSE) framework. This new formulation leads to a very interesting interpretation that allows the utilization of results from the study of constrained adaptive filters to understand the behavior of the deficient length LMS adaptive filter. The reduced number of coefficients is formulated as a linear optimization constraint that defines a projection onto the feasible space for the adaptive weight vector. We derive analytical models for the mean and mean-square behavior of the adaptive weights. In addition, we derive an analytical model for the variance of the steady-state squared estimation error which provides important design information. Simulation results show excellent matching between theory and actual algorithm behavior.

Direct integration bias-compensated maximum correntropy criterion algorithm independent of measurement noise samples

In system identification, if the filter input and the desired signal are both interfered by noise, traditional adaptive filtering algorithms will not work effectively. The recently presented bias-compensated normalized maximum correntropy criterion (BC-NMCC) algorithm, which was developed based on the information theory learning (ITL) and Taylor expansion, can deal with this case. However, it needs to use measurement noise samples to update the adaptive filter weight vector, whose values are usually unavailable. To solve this problem, we propose a direct integration bias-compensated maximum correntropy criterion (DI-BC-MCC) algorithm under an unbiasedness criterion (UC). Specifically, we utilize a direct integral approach to calculate the expected values instead of using Taylor expansion. With this idea, the update equation of DI-BC-MCC does not involve measurement noise samples, unlike BC-NMCC. The derived compensation term can reduce the impact of input noise significantly, and DI-BC-MCC can perform well in impulsive noise environments. In addition, the steady-state performance of DI-BC-MCC is analyzed under some frequently used assumptions. Finally, simulations are provided to demonstrate the good performance of DI-BC-MCC and to verify the accuracy of the theoretical analysis.

Enhanced approach to fusing automatic characteristic frequency extraction and adaptive array signals weighting for abnormal machine sound localization

In this paper, an enhanced approach for sound localization is proposed, which fuses automatic extraction of array signal characteristic frequencies and adaptive weighting. The method refines the autoregressive power spectral estimation algorithm and improves density-based spatial clustering of applications with noise algorithm for characteristic frequency extraction. Adaptive weighting technique is introduced to alleviate the problem of frequency mismatch in the localization process. The initial weight of narrowband signals is calculated and normalized using the frequency domain amplitude integration of narrowband signals, followed by adaptive threshold correction to eliminate invalid narrowband signal weights. The adaptive weight vector improves the localization method’s accuracy and interference suppression. The effectiveness and universality of the proposed method are demonstrated with test data from dry transformers and pumps, and its applicability is shown to extend to various spatial spectrum estimation algorithms and deep learning-based sound source localization techniques.

Semi-supervised multi-view concept decomposition

Concept Factorization (CF), as a novel paradigm of representation learning, has demonstrated superior performance in multi-view clustering tasks. It overcomes limitations such as the non-negativity constraint imposed by traditional matrix factorization methods and leverages kernel methods to learn latent representations that capture the underlying structure of the data, thereby improving data representation. However, existing multi-view concept factorization methods fail to consider the limited labeled information inherent in real-world multi-view data. This often leads to significant performance loss. To overcome these limitations, we propose a novel semi-supervised multi-view concept factorization model, named SMVCF. In the SMVCF model, we first extend the conventional single-view CF to a multi-view version, enabling more effective exploration of complementary information across multiple views. We then integrate multi-view CF, label propagation, and manifold learning into a unified framework to leverage and incorporate valuable information present in the data. Additionally, an adaptive weight vector is introduced to balance the importance of different views in the clustering process. We further develop targeted optimization methods specifically tailored for the SMVCF model. Finally, extensive experiments on four diverse datasets with varying label ratios demonstrated the effectiveness and superiority of the proposed SMVCF in multi-view clustering tasks.

Analysis of the Least Mean Square algorithm with processing delays in the adaptive arm for Gaussian inputs for system identification

This paper analyzes the effect of a processing delay on the Least Mean Squares (LMS) algorithm for a system identification problem when the processing delay is in the adaptive arm of the filter. Thus the sensing of the input signal is delayed. The input is assumed to be a zero mean stationary Gaussian process. The theoretical mean and mean square behavior of the adaptive weight vector is analyzed. The weight vector is shown to be biased and significantly affects the mean square deviation (MSD). Monte Carlo simulations are presented in support of the assumptions used to derive the theoretical model as a function of the delay, bandwidth and step-size for the LMS algorithm. The results suggest bias problems with other more complicated adaptive filtering algorithms such as Normalized LMS and Recursive Least Squares.

Decomposition-based interval multi-objective evolutionary algorithm with adaptive adjustment of weight vectors and neighborhoods

Interval multi-objective optimization problems (IMOPs) are one of the most critical optimization problems in practical applications. However, compared to deterministic multi-objective optimization problems (MOPs), there are few researchs addressing IMOP. In addition, the uncertainty contained in the problem makes the distribution of the population more challenging. Therefore, this paper proposed a decomposition-based interval multi-objective evolutionary algorithm with adaptive adjustment of weight vectors and neighborhoods (IMOEA/D-AWN). Firstly, an interval sparsity level function (ISL) is constructed to measure the density of individuals, and a comprehensive ranking of interval sparsity ranking and interval uncertainty ranking is proposed. For the purpose of improving the distribution of the population while reducing its uncertainty, based on the above comprehensive ranking, a new adaptive adjustment weight vector strategy guided by interval elite population is designed. Besides, an adaptive adjustment neighborhoods strategy is designed. This strategy adjusts individuals' neighborhood size according to the number of iterations to improve the efficiency of evolution. Finally, the IMOEA/D-AWN is evaluated on 17 interval benchmark test problems and a collaborative computation offloading optimization problem, and compared with four advanced multi-objective evolutionary algorithms with interval parameters (IMOEAs). Experimental results show that this algorithm performs well in convergence, diversity, and uncertainty.

A lightweight and anti‐collusion trust model combined with nodes dynamic relevance for the power internet of things

AbstractA large number of monitoring sensors are introduced in the power grid. However, the traditional trust models commonly used for edge‐side security management are weak in detecting large‐scale malicious interactions and collusion attacks. For that, a lightweight and anti‐collusion trust model combined with nodes’ dynamic relevance for the power Internet of Things (IoT) is proposed. Firstly, a global trust management system is constructed according to the working mechanism of sensors in the power grid. After that, trust feedback and contact frequency of the devices are combined to build an adaptive dynamic weight vector based on relevance volatility. Fluctuations in trust values are reduced and the trust difference between normal and malicious nodes is widened. An anti‐collusion algorithm based on contact set awareness is also designed to effectively detect collusion attacks. The checksum local broadcast is established in the trust model to counteract the risk of intelligent terminal failure. The results show that the trust model achieves 100% accuracy of node discrimination when the maximum proportion of malicious nodes is 20% in a 50‐node network scale. In addition, the calculation time of the overall model is 211 ms and the memory consumption is 161 kb, which is suitable for power IoT sensor networks.

Robust Adaptive Beamforming Based on a Convolutional Neural Network

To address the advancements in jamming technology, it is imperative to consider robust adaptive beamforming (RBF) methods with finite snapshots and gain/phase (G/P) errors. This paper introduces an end-to-end RBF approach that utilizes a two-stage convolutional neural network. The first stage includes convolutional blocks and residual blocks without downsampling; the blocks assess the covariance matrix precisely using finite snapshots. The second stage maps the first stage’s output to an adaptive weight vector employing a similar structure to the first stage. The two stages are pre-trained with different datasets and fine-tuned as end-to-end networks, simplifying the network training process. The two-stage structure enables the network to possess practical physical meaning, allowing for satisfying performance even with a few snapshots in the presence of array G/P errors. We demonstrate the resulting beamformer’s performance with numerical examples and compare it to various other adaptive beamformers.

Robust rank-one matrix completion with rank estimation

Matrix completion aims at estimating the missing entries of a low-rank and incomplete data matrix. It frequently arises in many applications such as computer vision, pattern recognition, recommendation system, and data mining. Most of the existing methods face two problems. Firstly, the data matrix in real world is often disturbed by noise. Noise may change the date structure of the incomplete matrix, thereby degrade the performance of matrix completion algorithms. Secondly, some existing methods need to preset a reasonable rank as input, and the value of rank will affect the performance of the algorithms. Therefore, we proposed a robust rank-one matrix completion method with rank estimation in this paper. To mitigate the influence of noise, we divide the incomplete and noisy data matrix into two parts iteratively: low-rank and sparse parts. Besides, we use a weighted rank-one matrix pursuit algorithm to approximate the low-rank part of the data matrix, and the rank of the matrix can be estimated with the adaptive weight vector. The performance of the proposed method is demonstrated by experiments on both synthetic datasets and image datasets. The experimental results demonstrate the performance of the proposed method with incompleted matrices distrubed by sparse noise.

Dual-graph regularized concept factorization for multi-view clustering

Matrix factorization is an important technology that obtains the latent representation of data by mining the potential structure of data. As two popular matrix factorization techniques, concept factorization (CF) and non-negative matrix factorization (NMF) have achieved excellent results in multi-view clustering tasks. Compared with multi-view NMF, multi-view CF not only removes the non-negative constraint but also utilizes the idea of the kernel to learn the latent representation of data. However, both of them ignore the local geometric structure in the nonlinear low-dimensional manifold. Furthermore, most of the existing CF-based methods are designed for single-view tasks, which cannot be directly applied to multi-view clustering tasks. To tackle the above shortcomings, we present a new multi-view clustering algorithm, called dual-graph regularized concept factorization for multi-view clustering (MVDGCF). Specifically, we first extend conventional single-view CF to a multi-view version, which can explore the complementary information of multi-view data more effectively. Then we develop a novel dual-graph regularization strategy, which can simultaneously capture the local structure information of the data space and feature space, respectively. Moreover, an adaptive weight vector is introduced to balance the importance of different views. Finally, extensive experiments are carried out on seven datasets. The results show that our method is superior to several popular multi-view clustering methods.

Real-Time Image-Based Vibration Extraction with Memory-Efficient Optical Flow and Block-Based Adaptive Filter

In this paper, we propose a real-time vibration extraction system, which extracts vibration component within a given frequency range from videos in real time, for realizing tremor suppression used in microsurgery assistance systems. To overcome the problems in our previous system based on the mean Lucas-Kanade (LK) optical flow of the whole frame, we have introduced a new architecture combining dense optical flow calculated with simple feature matching and block-based band-pass filtering using band-limited multiple Fourier linear combiner (BMFLC). As a feature of optical flow calculation, we use the simplified rotation-invariant histogram of oriented gradients (RIHOG) based on a gradient angle quantized to 1, 2, or 3 bits, which greatly reduces the usage of memory resources for a frame buffer. An obtained optical flow map is then divided into multiple blocks, and BMFLC is applied to the mean optical flow of each block independently. By using the L1-norm of adaptive weight vectors in BMFLC as a criterion, blocks belonging to vibrating objects can be isolated from background at low cost, leading to better extraction accuracy compared to the previous system. The whole system for 480p and 720p resolutions can be implemented on a single Xilinx Zynq-7000 XC7Z020 FPGA without any external memory, and can process a video stream supplied directly from a camera at 60fps.

Sparsity-Promoting Affine Projection Algorithm With Periodically-Updated Gain Matrix and Its Performance Analysis

Sparse system identification is often encountered in applications such as network and acoustic echo cancellation. This work applies the sparsity promoting method to the affine projection algorithm (APA) to develop a sparsity-promoting APA (SAPA). To reduce its computational complexity, the gain matrix of SAPA is periodically updated, which leads to a periodically updated gain matrix based SAPA (PSAPA). In addition, the steady-state and tracking performance of PSAPA is analyzed using an improved weighted energy conservation method, which takes account of the correlation between the adaptive filter weight vector and the noise vector. The results of performance analysis are also suited to other proportionate APAs (PAPAs). Simulation results verify the advantages of the proposed algorithms and show that the theoretical expressions on the steady-state and tracking performance can predict the stochastic behaviors well.

Interrupted-Sampling and Non-Uniform Periodic Repeater Jamming against mDT-STAP System

The difference between sampling data and detection data can degrade the performance of space-time adaptive processing (STAP). A jamming algorithm with a non-uniform periodic repeater based on interrupted-sampling is proposed against the reduced dimensional space-time adaptive processing (STAP) system for the first time. Firstly, the model of m-bins doppler transform (mDT) STAP training and processing signal samples is described. Then, the method of false targets generated by the non-uniform periodic repeater is analyzed theoretically based on the principle of interrupted-sampling. The simulation shows that numerous false targets with different amplitude and intervals can be generated by changing the retransmitted parameters. The independent identical distribution (IID) of system sample data can be destroyed after these false targets are received by the radar system, and the main lobe will be distorted when the system’s adaptive weight vector is formed. The processing performance of the mDT-STAP system is seriously degraded. The jamming method proposed based on interrupted-sampling and the non-uniform periodic repeater offers great potential for the interference research on STAP in real conditions.

Handling Irregular Many-Objective Optimization Problems via Performing Local Searches on External Archives

Adaptive weight-vector adjustment has been explored to compensate for the weakness of the evolutionary many-objective algorithms based on decomposition in solving problems with irregular Pareto-optimal fronts. One essential issue is that the distribution of previously visited solutions likely mismatches the irregular Pareto-optimal front, and the weight vectors are misled towards inappropriate regions. The fact above motivated us to design a novel many-objective evolutionary algorithm by performing local searches on an external archive, namely, LSEA. Specifically, the LSEA contains a new selection mechanism without weight vectors to alleviate the adverse effects of inappropriate weight vectors, progressively improving both the convergence and diversity of the archive. The solutions in the archive also feed back the weight-vector adjustment. Moreover, the LSEA selects a solution with good diversity but relatively poor convergence from the archive and then perturbs the decision variables of the selected solution one by one to search for solutions with better diversity and convergence. At last, the LSEA is compared with five baseline algorithms in the context of 36 widely-used benchmarks with irregular Pareto-optimal fronts. The comparison results demonstrate the competitive performance of the LSEA, as it outperforms the five baselines on 22 benchmarks with respect to metric hypervolume.

An automatic fuzzy monitoring method of underground rock moisture permeation damage based on MAE fractal

Moisture permeation would affect the stability of underground rock. It is of great significance to monitoring the moisture states in advance for the engineering safety. In this research, a fuzzy on-line monitoring method of rock moisture permeation was proposed. First, intermittent AE (Acoustic Emission) was acquired and the AW (A Wave) component was separated using sliding scanning PSD (Power Spectrum Decomposition). Then, four modal AE parameters were extracted and recombined. Fractal correlation dimension indicators were calculated to obtain the complexity of each parameter. Finally, the adaptive weight vector and membership matrix were constructed based on the statistics fluctuation of monitoring data. The moisture permeation state was recognized through the fuzzy calculation. Experiment simulated the moisture permeation of underground rock in engineering applicability. The results demonstrated the advantages in terms of real time performance, reliability as well as perceptiveness.

Multiple Mainlobe Interferences Suppression Based on Eigen-Subspace and Eigen-Oblique Projection.

When the desired signal and multiple mainlobe interferences coexist in the received data, the performance of the current mainlobe interference suppression algorithms is severely challenged. This paper proposes a multiple mainlobe interference suppression method based on eigen-subspace and eigen-oblique projection to solve this problem. First, use the spatial spectrum algorithm to calculate interference power and direction. Next, reconstruct the eigen-subspace to accurately calculate the interference eigenvector, then generate the eigen-oblique projection matrix to suppress mainlobe interference and output the desired signal without distortion. Finally, the adaptive weight vector is calculated to suppress sidelobe interference. Through the above steps, the proposed method solves the problem that the mainlobe interference eigenvector is difficult to select, caused by the desired signal and the mismatch of the mainlobe interference steering vector and its eigenvector. The simulation result proves that our method could suppress interference more successfully than the former methods.

Adaptive weighted robust iterative closest point

The Iterative Closest Point (ICP) algorithm is one of the most important methods for rigid registration between point sets. However, its performance begins to degenerate with the point data are overly contaminated by noise, outliers, and missing data. In this paper, we propose an adaptive weighted robust ICP method (AW-RICP). A sparse weight vector can be automatically learned by adaptive neighbors assigning process. The sparseness of the weight vector can be achieved by fitting the number of selected samples. The adaptive weight vector leads to the robustness of AW-RICP by eliminating the negative effect caused by point cloud pairs with largest registration errors. Further, the retained point pairs are assigned suitable weights to suppress the noises and outliers. The new error metric can effectively improve the robustness of ICP method. Additionally, we propose an efficient iterative solution to optimize our problem. Experiments on both synthetic and real data sets show that the proposed method can achieve superior performance with other state-of-the-art methods.

A decomposition-based many-objective evolutionary algorithm with adaptive weight vector strategy

Evolutionary multi-objective optimization methods have become increasingly popular in finding a representative set of Pareto optimal solutions for multi-objective optimization problems (MOPs). As an important multi-objective optimization method, MOEA/D has been successfully applied to resolve various of MOPs. However, there still exist two issues in MOEA/D. First, the distribution of result set is greatly limited in complex Pareto Front (PF) shapes. Second, the effectiveness is relatively poor for solving many-objective optimization problems (MaOPs). Although many researchers attempt to improve MOEA/D, these two issues have not been solved well. This paper proposes a modified MOEA/D method called MOEA/D-VW which involves three optimization strategies. First, an adaptive weight vector adjustment strategy is adopted to fine-tune the subproblems, thus changing the evolution direction of the subpopulation. Second, a weight vector initialization strategy with preference parameters is added into MOEA/D-VW. Third, a modified crossover operator is leveraged to generate new population with good diversity and overcome the problem of high computational cost. Experiments are carried out on the set of 23 continuous optimization problems. The experimental results show that the performance and the distribution of the Pareto Set (PS) of MOEA/D-VW are effectively improved. Meanwhile, the experimental results demonstrate that the modified crossover operator can effectively reduce the computational cost of MOEA/D-VW.

Block-sparse sign algorithm and its performance analysis

System identification is often encountered in applications such as echo cancellation, active noise control, and channel equalization. If the unknown system is sparse, using sparsity-induced methods can improve the convergence performance. Recently, the l2,0-norm constraint was used to derive a block-sparse LMS (BS-LMS) algorithm to accelerate convergence for identifying multi-clustering sparse systems. In some cases, output of the unknown system is contaminated by impulsive noise, and BS-LMS performs poorly or even diverges when identifying such systems. To address this problem, this paper constructs a loss function by combining the absolute error and the l2,0-norm of adaptive filter weight vector, and then uses the subgradient descent method to develop a block-sparse sign algorithm (BS-SA). Its mean and mean-square performance is also analyzed based on the Gaussian-Bernoulli impulsive noise model under some frequently used assumptions. Finally, simulations are performed to test the robustness of BS-SA against impulsive noise and to evaluate the accuracy of theoretical expressions derived for statistical performance.