Search

The fusion of the A* and the dynamic windowing algorithm is commonly used for the path planning of mobile robots in dynamic environments. However, the planned path has the problems of redundancy and low security. This paper proposes a path planning algorithm based on the safety distance matrix and adaptive weight adjustment strategy to address the above problems. Firstly, the safety distance matrix and new heuristic function are added to the traditional A* algorithm to improve the safety of global path. Secondly, the weight of the evaluation sub-function in the dynamic window algorithm is adjusted through an adaptive weight adjustment strategy to solve the problem of path redundancy. Then, the above two improved algorithms are fused to make the mobile robot have dynamic obstacle avoidance capability by constructing a new global path evaluation function. Finally, simulations are performed on grid maps, and the fusion algorithm is applied to the actual mobile robot path planning based on the ROS. Simulation and experimental results show that the fusion algorithm achieves optimization of path safety and length, enabling the robot to reach the end point safely with real-time dynamic obstacle avoidance capability. [ABSTRACT FROM AUTHOR]

In order to analyze the relay action process from an imaging perspective and further investigate the bounce phenomenon of relay contacts during the contact process, this paper utilizes a high-speed shooting platform to capture images of relay action. In light of the situation where the stationary contact in the image is inclined and continuously changing, a rotation template matching algorithm based on adaptive weight is proposed. The algorithm identifies and obtains the inclination angle of the stationary contact, enabling the study of the relay contact bounce process. By extracting contact bounce distance data from the images, a bounce process curve is plotted. Combined with the analysis of the contact bounce process, the reasons for the bounce are explored. The results indicate that the proposed rotation template matching algorithm can accurately identify stationary contacts and their angles at different angles. By analyzing the contact status and bounce process of the relay contacts in conjunction with the relay structure, parameters such as the bounce time, bounce height, and time required to reach the maximum distance can be calculated. Additionally, the main reason for contact bounce in the relay studied in this paper is the limitation imposed on the continued movement of the stationary contact by the presence of the relay brackets when the kinetic energy of the contact is too high. This phenomenon occurs during the first vibration peak in the vibration process after the moving contact contacts the stationary contact. The research results provide a reference for further studying the relay contact bounce process, optimizing relay structure, and suppressing contact bounce. [ABSTRACT FROM AUTHOR]

Collaborative representation-based classification (CRC) has been extensively applied to various recognition fields due to its effectiveness and efficiency. Nevertheless, it is generally suboptimal for imbalanced learning. Previous studies have revealed that a class-imbalance distribution can lead CRC, and even most conventional classification methods, to ignore the minority class and prioritize the majority class. To address this deficiency, this paper proposes a hybrid density-based adaptive weighted collaborative representation model that incorporates a regularization technique and an adaptive weight generation mechanism into the CRC framework. A new regularization term, based on class-specific representation, is introduced to decrease the correlation between classes and enhance CRC's discriminative ability. The sample distribution and density information within and between classes are employed to assign greater weights to minority samples, thereby strengthening the representation capabilities of minority samples and reducing the bias towards the majority class. Furthermore, it is theoretically demonstrated that this model has a closed-form solution. Its complexity is comparable to that of CRC, ensuring its efficiency. Extensive experiments on diverse data sets from the KEEL repository show the superiority of the proposed method compared to other state-of-the-art imbalanced classification methods. [ABSTRACT FROM AUTHOR]

Based on the impact of epidemic prevention and control, the floating population supervision department classifies and controls the floating population by industry. There are many personnel management and control points. When the computer-aided management system is used, the outdoor environment is complex and the data interference is large. Therefore, the recognition accuracy of outdoor scenery is required to be higher. In this paper, a convolutional neural network with adaptive weights is proposed. In this method, the feature fusion strategy is combined with the network, and the optimal feature weight is obtained by training the network. In addition, this paper uses multiple two classifiers instead of multiple classifiers to achieve accurate target classification. Experiments show that the method proposed in this paper has excellent performance in the detection of similar objects. The strategy of replacing multi classification network with multi classification network improves the accuracy and recall of target detection in known environment. [ABSTRACT FROM AUTHOR]

In this paper, the BP neural network optimized by an improved sparrow search algorithm is proposed (WLT-SSA-BP), which performs excellently in the classification task of strip steel defect images. In the current work, an adaptive weight is introduced into the WLT-SSA algorithm, and the weight is affected by the number of population iterations and the size of the fitness value, which enhances the global search ability of the algorithm; A Levy flight strategy is introduced into WLT-SSA, which helps the algorithm jump out of the local optimal solution through a short-distance local search and occasional longer-distance walking; At the same time, the population t distribution strategy is introduced into the population initialization, which effectively prevents the aggregation of the population. Finally, the proposed WLT-SSA and BP neural network are modeled. The experimental results show that the accuracy rate of WLT-SSA-BP in classifying defect images can reach 96.62%, which is comparable to some other typical heuristic algorithm-optimized BP networks. Its accuracy, precision, recall, specificity, and F1 score were increased by 0.5%–4.66%, 2.62%–8.1%, 1.71%–7.77%, 0.72%–1.33%, 1.59%–8.73%, respectively. [ABSTRACT FROM AUTHOR]

This paper intends to develop a novel framework for text document clustering with the aid of a new improved meta-heuristic algorithm. Initially, the features are selected from the text document by subjecting each word under Term Frequency-Inverse Document Frequency (TF-IDF) computation. Subsequently, centroid selection plays a vital role in cluster formation, which is done using a new Improved Lion Algorithm (LA) termed as Cross over probability-based LA model (CP-LA). As a novelty, this paper introduced a new inter and intracluster similarity model. Moreover, this centroid selection is made in such a way that the proposed adaptive weighted similarity should be minimal. Based on the characteristics of the document, the weights are automatically adapted with the similarity measure. The proposed adaptive weighted similarity function involves the inter-cluster, and intra-cluster similarity of both ordered and unordered documents. Finally, the superiority of the proposed over other models is proved under different performance measures. [ABSTRACT FROM AUTHOR]

In order to solve the problems of inadequate global search and easy to fall into local extremum, this paper proposed a multi-strategy fusion improved adaptive tunicate swarm algorithm（MITSA）. Firstly, this paper used the best point set strategy to improve population diversity during initialization. Secondly, it offered a multi-elite cooperative guidance mechanism to optimize the tunicates’ location information, and enhance the global exploration ability of the algorithm by increasing the exploration possibility of unknown search area. Then, the algorithm achieved dynamic global and local search balance by introducing adaptive weight factors into the group behavior stage. Meanwhile, probabilistic wavelet variation strategy promoted individual dynamic fine-tuning to enhance the anti-stagnation ability of the algorithm, while using the greedy principle to retain excellent information to help the population to the food source. Finally, this paper proved the global convergence of the improved algorithm based on Markov chain theory. Through the numerical simulation of the benchmark test function and CEC2014 complex function, the experimental results and Wilcoxon rank sum test results comprehensively verify MITSA’s excellent convergence accuracy, robust robustness and high-dimensional scalability. [ABSTRACT FROM AUTHOR]

Fuzzy c-means clustering algorithm (FCM), as the most widely used clustering algorithm, works by iteratively updating the membership degree and the cluster centers to improve the effectiveness of clustering. The performance of FCM algorithm is chiefly evaluated by intra-cluster compactness and inter-cluster separation. However, it has some defects such as high dependency on the initial cluster centers, sensitivity to the noise samples and outliers, difficulties in obtaining the optimization of hyperparameters, a fairly poor performance on datasets with the nonuniform distribution. The main purpose of this paper is to tackle these issues. The novelty of this paper is three-fold: 1) a new FCM clustering algorithm (i.e., CWAFCM) has been proposed, which has a good capability of performing the clustering on datasets with nonuniform distribution and reducing the high dependency on the initial cluster centers; 2) considering the merits of AFCM-SP in removing noise samples and CWAFCM in performing clustering on datasets with nonuniform distribution, a combination of the objective functions of these two clustering algorithms is developed to construct the hybrid AFCM algorithm; and 3) during the parameter setting by means of the PSO algorithm with time-varying acceleration coefficients (PSO-TVAC), a new index, namely adaptive clustering validity index (ACVI), is presented to describe the intra-cluster compactness and the inter-cluster separation in a proper manner. Experiments on six data sets in UCI and one artificial data set have been carried out with a comparison of five well-known FCM algorithms. Experimental results have demonstrated that the proposed hybrid AFCM with adaptive weights can more effectively enhance the performance of FCM to increase the clustering effectiveness than the contrastive algorithms. The ranks for seven algorithms on seven datasets in terms of CVIXB, accuracy, and normalized mutual information(NMI), further verifying the superiority of the new algorithm. Therefore it can be concluded that the proposed hybrid AFCM algorithm performs well in reducing the reliance on the initial cluster centers and the sensitivity to the noise and outliers. [ABSTRACT FROM AUTHOR]

In image super-resolution, the existing convolution neural network methods increase the number of network layers and filters to achieve better performance, and seldom consider the influence of different branches in feature extraction on the reconstruction effect, which leads to the problems of blurred details and unclear visual perception. Therefore, we propose an adaptive weight adjustment super-resolution (AWSR) reconstruction model in this paper. The model includes Shallow Feature Extraction (SFE), Information Extraction Enhancement Block (IDEB) and Reconstruction Block (RB). IDEB composed of Adaptive Weight Blocks (AWB) and Channel Linking Layers (CLL) learns a deeper mapping relationship between LR image and HR image by adaptively adjusting the proportions of different branches. It not only saves computational cost, but also improves the expression ability of the model. Meanwhile, the performance of the model is further improved by dimension change in the up-sample block. Especially, the image edge and texture reconstruction effects are obviously improved. Compared with SRNHARB algorithm proposed in 2021, the PSNR values are increased by 0.23 dB, 0.19 dB and 0.02 dB at × 2 , × 3 , × 4 on the Set5 dataset. Moreover, the proposed model has a strong generalization ability, and the reconstructed SR images can achieve satisfactory results. [ABSTRACT FROM AUTHOR]

Data-driven decision-making is the process of using data to inform your decision-making process and validate a course of action before committing to it. The quality of unlabeled data in real-world scenarios presents challenges for semi-supervised learning. Effectively leveraging unlabeled data for learning is challenging due to the need for labeled information, while the scarcity of labeled data requires efficient and flexible data augmentation methods. To address these challenges, this paper proposes the AatMatch algorithm, which uses a momentum model, coarse learning, and adversarial training to generate adversarial examples for different classes. The algorithm sets the threshold for generating pseudo-labels and reinforces the results with adversarial perturbations based on evaluation results. In addition, a more refined learning strategy for unlabeled data is adjusted by setting adaptive weights based on the confidence of each unlabeled data point, thereby mitigating the adverse effects of low-confidence unlabeled data on the model. Experimental evaluations on several datasets, including CIFAR-10, CIFAR-100, and SVHN, demonstrate the effectiveness of the proposed AatMatch algorithm in semi-supervised learning. Specifically, the algorithm achieves the lowest error rates for multiple scenarios on these datasets. [ABSTRACT FROM AUTHOR]

To improve the controllability and interpretability of image captioning generation, an adaptive optimization strategy for controllable image captioning is proposed. In this paper, we adopt an encoder-decoder structure, in which the encoder is used to detect the regions of interest (ROIs) of the image while the decoder is applied to generate sentences. Between the encoder and decoder, we leverage a sorting network to obtain a set of ordered regions as the input of the decoder. Moreover, we propose an adaptive weight learning algorithm, which can make the multiple loss functions better participate in training. In addition, we introduce a multibranch decision strategy to optimize the output. The experimental results, which are conducted on COCO Entities and Flickr30k Entities datasets, demonstrate that the accuracy of control has been significantly improved and transcends the state-of-the-art methods by a large margin under Cider and Spice which are relatively important indicators. [ABSTRACT FROM AUTHOR]

This paper proposes a multi-objective optimization method using an adaptive weight determination scheme and tunneling method. To find the optimum designs that are evenly distributed on the Pareto front, the weights of different objective functions are adaptively determined by using the concept of a hyperplane so that new solutions can be gradually found in the objective space. In addition, to avoid locally optimized solutions that are dominated by other Pareto optimum designs, a tunneling method is employed in the optimization process. To confirm the effectiveness of the proposed method, topology optimization of the magnetic actuator is performed. The magnetic force and volume of the actuator are considered as two conflicting objective functions in the optimization problem, and Pareto optimum solutions that are evenly distributed in the objective space could be obtained. [ABSTRACT FROM AUTHOR]

Risk management is an important aspect of financial research because correlations among financial data are essential in evaluating portfolio risk. Among various correlations, spatiotemporal correlations involve economic entity attributes and are interrelated in space and time. Such correlations have therefore drawn increasing attention in financial risk management. However, classical correlation measurements are typically based on either time series correlations or spatial dependence; they cannot be directly applied to financial data with spatiotemporal correlations. The spatiotemporal correlation coefficient model with adaptive weight proposed in this paper can (1) address the absolute quantity, dynamic quantity, and dynamic development of financial data and (2) be used for risk grading, financial risk evaluation, and portfolio management. To verify the validity and superiority of this model, cluster analysis results and portfolio performance are compared with a classical model with time series correlation or spatial correlation, respectively. Empirical findings show that the proposed coefficient is highly effective and convenient compared to others. Overall, our method provides a highly efficient financial risk management method with valuable implications for investors and financial institutions. [ABSTRACT FROM AUTHOR]

Due to complex background and volatile object shape-appearance in image, the stability and accuracy of tracking algorithm is often disturbed and reduced. So how to accurately and robustly track object in object tracking application is a challenge topic at home and abroad. Built upon the methodologies of compressive tracking and spatio-temporal context, a simple yet robust object tracking method is proposed for solving the drift and occlusion problems in paper. It combines two existing classical ideas into a single framework: adaptive weighted idea and occlusion detection mechanism. In order to weaken interference problems of object background, object area is firstly partitioned into equal-sized sub-patches and the different weight related with location information is assigned for each patch; Then, for improving its robustness, Bhattacharyya distance is adopted to find out these samples with maximum discrimination; In addition, our proposed occlusion detection mechanism is for recapturing the tracked object when occlusion occurs. Many simulation experiments show that our proposed algorithm achieves more favorable performance than these existing state-of-theart algorithms in handing various challenging infrared videos, especially occlusion and shape deformation. [ABSTRACT FROM AUTHOR]

Satisfying the process technical requirements while optimizing the control of oxygen and zinc oxide is the main task for optimal operation of the iron removal process. However, due to the complicated mechanism and varied production conditions, the process is difficult to achieve optimal operation with the simple controller. The manual control, as a result, is extensively used in practice. In this paper, we develop an optimal setting and control (OSC) system for the iron removal process to achieve its technical requirements with minimal process consumptions. The OSC system is composed of a neural network soft-sensor, an optimal setting module, an optimal controller, and a fuzzy-logic-based compensator. First, we define the oxygen reaction efficiency (ORE) to measure the difference between the theoretical oxygen amount and its actual amount. Due to the ORE cannot be measured online and it varies with the production conditions, an adaptive weight radial basis function neural network soft-sensor is designed to estimate it. The adaptive weight adjusting method contributes to improve the adaptability of the soft-sensor, and its convergence is discussed. The optimal setting module provides the set-point of outlet ferrous ion concentration for the optimal operation of every reactor. The steady-state optimal control of oxygen and zinc oxide is then established, and the compensator compensates the control inputs utilizing the feedforward and feedback information. Finally, simulations validate that the ORE is important for the optimal control of the process. Furthermore, industrial experiments are presented to verify the effectiveness and potential of the proposed strategy. [ABSTRACT FROM AUTHOR]

In the Unmanned Aerial Vehicle (UAV) system, finding a flight planning path with low cost and fast search speed is an important problem. However, in the complex three-dimensional (3D) flight environment, the planning effect of many algorithms is not ideal. In order to improve its performance, this paper proposes a UAV path planning algorithm based on improved Harris Hawks Optimization (HHO). A 3D mission space model and a flight path cost function are first established to transform the path planning problem into a multidimensional function optimization problem. HHO is then improved for path planning, where the Cauchy mutation strategy and adaptive weight are introduced in the exploration process in order to increase the population diversity, expand the search space and improve the search ability. In addition, in order to reduce the possibility of falling into local extremum, the Sine-cosine Algorithm (SCA) is used and its oscillation characteristics are considered to gradually converge to the optimal solution. The simulation results show that the proposed algorithm has high optimization accuracy, convergence speed and robustness, and it can generate a more optimized path planning result for UAVs. [ABSTRACT FROM AUTHOR]

The single batch normalization (BN) method is commonly used in the instance segmentation algorithms. The batch size is concerned with some drawbacks. A too small sample batch size leads to a sharp drop in accuracy, but a too large batch may result in the memory overflow of graphic processing units (GPU). These problems make BN not feasible to some instance segmentation tasks with inappropriate batch sizes. The self-adaptive normalization (SN) method, with an adaptive weight loss layer, shows good performance in instance segmentation algorithms, such as the YOLACT. However, the parameter averaging mechanism in the SN method is prone to problems in the weight learning and assignment process. In response to such a problem, the paper proposes to replace the single BN with an adaptive weight loss layer in SN models, based on which a weight learning method is developed. The proposed method increases the input feature expression ability of the subsequent layers. By building a Pytorch deep learning framework, the proposed method is validated in the MS-COCO data set and Autonomous Driving Cityscapes data set. The experimental results prove that the proposed method is effective in processing samples independent from the batch size. The stable accuracy for all kinds of target segmentation is achieved, and the overall loss value is significantly reduced at the same time. The convergence speed of the network is also improved. [ABSTRACT FROM AUTHOR]

Fuzzy c-means clustering algorithm (FCM) often used in pattern recognition is an important method that has been successfully used in large amounts of practical applications. The FCM algorithm assumes that the significance of each data point is equal, which is obviously inappropriate from the viewpoint of adaptively adjusting the importance of each data point. In this paper, considering the different importance of each data point, a new clustering algorithm based on FCM is proposed, in which an adaptive weight vector W and an adaptive exponent p are introduced and the optimal values of the fuzziness parameter m and adaptive exponent p are determined by SA-PSO when the objective function reaches its minimum value. In this method, the particle swarm optimization (PSO) is integrated with simulated annealing (SA), which can improve the global search ability of PSO. Experimental results have demonstrated that the proposed algorithm can avoid local optima and significantly improve the clustering performance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at the problems of the basic sparrow search algorithm (SSA) in terms of slow convergence speed and the ease of falling into the local optimum, the chaotic mapping strategy, adaptive weighting strategy and t-distribution mutation strategy are introduced to develop a novel adaptive sparrow search algorithm, namely the CWTSSA in this paper. In the proposed CWTSSA, the chaotic mapping strategy is employed to initialize the population in order to enhance the population diversity. The adaptive weighting strategy is applied to balance the capabilities of local mining and global exploration, and improve the convergence speed. An adaptive t-distribution mutation operator is designed, which uses the iteration number t as the degree of freedom parameter of the t-distribution to improve the characteristic of global exploration and local exploration abilities, so as to avoid falling into the local optimum. In order to prove the effectiveness of the CWTSSA, 15 standard test functions and other improved SSAs, differential evolution (DE), particle swarm optimization (PSO), gray wolf optimization (GWO) are selected here. The compared experiment results indicate that the proposed CWTSSA can obtain higher convergence accuracy, faster convergence speed, better diversity and exploration abilities. It provides a new optimization algorithm for solving complex optimization problems. [ABSTRACT FROM AUTHOR]

In order to make full use of the direct yaw control (DYC) in electric vehicles with four in-wheel motors (IWMs), this paper presents an adaptive SMC control scheme to improve the handling and stability based on a novel stability index proposed to quantitatively represent stability level. Firstly, a vehicle stability evaluation method is designed based on the front and rear tire slip angles phase plane and the quantitative stability index is derived according to the area where the states stay and the changing trend of the states. Secondly, a sliding mode controller (SMC) is designed to track the reference obtained by a two degrees of freedom (DoF) vehicle model as the desired vehicle motion. To enhance both vehicle handling and stability, the weight of the sliding surface is adaptively scheduled according to this stability index. The torque of each wheel is then distributed by solving the optimal adhesion rate consumption problem. Finally, the effectiveness of the proposed method is verified by CarSim–Simulink co-simulation. The simulation results illustrate that the proposed method can effectively improve vehicle handling and stability and has good robustness for the uncertainties of vehicle sideslip angle and road friction coefficient. [ABSTRACT FROM AUTHOR]

In order to analyze the relay action process from an imaging perspective and further investigate the bounce phenomenon of relay contacts during the contact process, this paper utilizes a high-speed shooting platform to capture images of relay action. In light of the situation where the stationary contact in the image is inclined and continuously changing, a rotation template matching algorithm based on adaptive weight is proposed. The algorithm identifies and obtains the inclination angle of the stationary contact, enabling the study of the relay contact bounce process. By extracting contact bounce distance data from the images, a bounce process curve is plotted. Combined with the analysis of the contact bounce process, the reasons for the bounce are explored. The results indicate that the proposed rotation template matching algorithm can accurately identify stationary contacts and their angles at different angles. By analyzing the contact status and bounce process of the relay contacts in conjunction with the relay structure, parameters such as the bounce time, bounce height, and time required to reach the maximum distance can be calculated. Additionally, the main reason for contact bounce in the relay studied in this paper is the limitation imposed on the continued movement of the stationary contact by the presence of the relay brackets when the kinetic energy of the contact is too high. This phenomenon occurs during the first vibration peak in the vibration process after the moving contact contacts the stationary contact. The research results provide a reference for further studying the relay contact bounce process, optimizing relay structure, and suppressing contact bounce.

This paper presents a multi-objective topology optimization method for a magnetic actuator design considering both magnetic force and actuator volume. We use a gradient-based optimization algorithm and the multi-objective optimization problem is formulated using a weighted sum of the objective functions. An adaptive weight determination scheme is iteratively employed to update the weighting coefficients of the objective functions to obtain non-dominated solutions. To ensure that the optimal solutions are evenly distributed in the objective domain, $\varepsilon $ -equality constraints are applied in the empty regions of the non-dominated solutions. The values of the constraints are determined by considering the distance ratios of the objective functions. The optimization problem is formulated to maximize the magnetic force and minimize the volume of the actuator. A level set function is used as a topological design variable to obtain optimal designs that have clear structural boundaries. [ABSTRACT FROM AUTHOR]

Fault detection of nonlinear dynamic processes can ensure the safety of industrial production processes. Industrial process data are mostly autocorrelated along with strong nonlinear characteristics. And these significant characteristics interact with each other and limit the fault detection performance of traditional methods. Therefore, this paper presents a novel adaptive fault detection method for nonlinear dynamic processes based on kernel entropy component analysis (KECA) integrating the moving window of dissimilarity (DMW) (KECA-DMW). The KECA is used to map the raw data and capture the nonlinear features of the data, which combine with moving window techniques to build the fault detection model. In the process of updating the data in the moving window, the data information of the historical window is combined with that of the current window to obtain a more comprehensive judgment of the current moment. Then a dynamic update fusion method with adaptive weight allocation based on the dissimilarity index is proposed by analyzing the data characteristics of window information at different moments through the dissimilarity. Finally, three example studies with a numerical example, a closed-loop continuously stirred tank reactor and a Tennessee-Eastman process are used to validate the effectiveness of the proposed method. Compared with other nonlinear dynamic process fault detection methods, the results verify the effectiveness of the proposed method in the process monitoring performance of nonlinear dynamic processes in terms of false alarm rate and fault detection rate, where the false alarm rates of the proposed method are only 2%, 1.83%, and 4.33%, while the fault detection rates are 97.4%, 96.83%, and 86.25%, respectively. [Display omitted] • Novel adaptive fault detection method based on the KECA-DMW is proposed. • The proposed method adaptively assigns weights from different windows. • The proposed method captures structural changes in complex process data. • The proposed method reduces the impact of autocorrelation on fault detection. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Multi-view clustering refers to the task of partitioning numerous unlabeled multimedia data into several distinct clusters using multiple features. In this paper, we propose a novel nonlinear method called joint learning multi-view clustering (JLMVC) to jointly learn kernel representation tensor and affinity matrix. The proposed JLMVC has three advantages: (1) unlike existing low-rank representation-based multi-view clustering methods that learn the representation tensor and affinity matrix in two separate steps, JLMVC jointly learns them both; (2) using the “kernel trick,” JLMVC can handle nonlinear data structures for various real applications; and (3) different from most existing methods that treat representations of all views equally, JLMVC automatically learns a reasonable weight for each view. Based on the alternating direction method of multipliers, an effective algorithm is designed to solve the proposed model. Extensive experiments on eight multimedia datasets demonstrate the superiority of the proposed JLMVC over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Aiming at the high mismatching rate of traditional local stereo matching algorithm at the depth discontinuities, this paper proposed an occlusion information stereo matching approach based on adaptive weight. Firstly, left-right consistency check algorithm detected the occlusion area of the reference image and the target image . Then, this paper utilized occlusion information to reduce the weight of pixels in the occlusion area at the process of cost aggregation, and scanline propagation filled occlusion pixels with horizontally nearest points in the disparity refinement stage. Finally, it calculated the mismatching rate of disparity map according to the Middlebury standard image dataset. The experimental results show that compared with adaptive support weight approach, the proposed approach decreases the mismatching rate by 16%. Meanwhile, it not only has lower mismatching rate in the depth discontinuous region, but also improves the accuracy of algorithm matching. [ABSTRACT FROM AUTHOR]

• Multi-level style differences are introduced to alleviate scenario sensitivity. • A bi-aggregation module provides the enhanced feature and initial mask. • A self-merging module is designed to adaptively reduce prototype bias. Few-shot Semantic Segmentation (FSS) attempts to segment the new category with only a few labeled samples, presenting a significant challenge. Existing approaches primarily focus on leveraging category information from the support set to identify objects of the new category in the query image. However, these models often struggle when confronted with substantial differences between paired images. To address issues stemming from scenario differences and intra-class diversity, this paper proposes an adaptive similarity-guided self-merging network. Firstly, style differences of multi-level features are introduced to alleviate the network's sensitivity to scenario variations and learn an adaptive weight for the K-shot scheme. Secondly, a feature-mask bi-aggregation module is designed to learn an enhanced feature and an initial mask for the query image. Within this module, dynamic correlations cover all the spatial locations, providing global information crucial for feature and mask aggregation. Subsequently, a self-merging module is proposed to alleviate prototype bias. It merges a self-prototype derived from the initial mask with an adaptive weighted support prototype obtained from K support images. Finally, the target object is segmented using the enhanced feature and merging prototype, and segmentation results are further refined by predictions of base categories and an adjustment factor derived from multi-level style differences. The proposed method achieves 69.1% (1-shot) and 72.3% (5-shot) mIoU on the PASCAL-5i dataset, and 47.4% (1-shot) and 52.1% (5-shot) mIoU on the COCO-20i dataset. These results demonstrate state-of-the-art segmentation performance compared to mainstream methods. © 2017 Elsevier Inc. All rights reserved. [ABSTRACT FROM AUTHOR]

Class imbalance problems pose significant challenges in the field of data mining. The skewed distribution of classes in imbalanced datasets often leads conventional classification methods to neglect the importance of minority classes, favoring the majority ones. In this paper, we propose an imbalanced complemented subspace representation model with adaptive weight learning to address imbalanced classification challenges. This approach incorporates a novel regularization technique and an adaptive weighting mechanism. The regularization technique integrates a complemented subspace term based on space theory into the efficient collaborative representation-based classification (CRC) framework, enhancing the overall accuracy of existing CRC-based methods. Furthermore, it takes into account both intra-class and inter-class density information to assign greater weights to minority classes. This highlights the contribution of minority classes and mitigates bias towards majority classes. Additionally, it is demonstrated that the proposed model can be efficiently solved with a closed-form solution. Extensive experiments conducted on diverse imbalanced datasets showcase the superiority of our method over most state-of-the-art imbalanced classification algorithms. • A complemented subspace regularization term is introduced into CRC. • An adaptive weight learning strategy is present. • The closed-form solution is provided to ensure the efficiency of our model. • Experimental results show the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Supplier evaluation is of great significance in green supply chain management. Influenced by factors such as economic globalization, sustainable development, a holistic index framework is difficult to establish in green supply chain. Furthermore, the initial index values of candidate suppliers are often characterized by uncertainty and incompleteness and the index weight is variable. To solve these problems, an index framework is established after comprehensive consideration of the major factors. Then an adaptive weight D-S theory model is put forward, and a fuzzy-rough-sets-AHP method is proposed to solve the adaptive weight in the index framework. The case study and the comparison with TOPSIS show that the adaptive weight D-S theory model in this paper is feasible and effective. [ABSTRACT FROM AUTHOR]

Summary: Finding an optimum design that satisfies all performances in a design problem is very challenging. To overcome this problem, multiobjective optimization methods have been researched to obtain Pareto optimum solutions. Among the different methods, the weighted sum method is widely used for its convenience. However, since the different weights do not always guarantee evenly distributed solutions on the Pareto front, the weights need to be determined systematically. Therefore, this paper presents a multiobjective optimization using a new adaptive weight determination scheme. Solutions on the Pareto front are gradually found with different weights, and the values of these weights are adaptively determined by using information from the previously obtained solutions' positions. For an n‐objective problem, a hyperplane is constructed in n ‐dimensional space, and new weights are calculated to find the next solutions. To confirm the effectiveness of the proposed method, benchmarking problems that have different types of Pareto front are tested, and a topology optimization problem is performed as an engineering problem. A hypervolume indicator is used to quantitatively evaluate the proposed method, and it is confirmed that optimized solutions that are evenly distributed on the Pareto front can be obtained by using the proposed method. [ABSTRACT FROM AUTHOR]

Imaging photoplethysmography (iPPG) is a non-contact measuring technology for several physiological parameters reflecting personal health status without a special sensor. However, the pulse signal obtained using the iPPG usually is contaminated by various noises, and the intensity of the interesting pulse signal is relatively weak compared to the noises, emphasizing the necessity of obtaining high-quality pulse signals to measure physiological parameters correctly. Various regions of the face harbor distinct pulse information. We propose a spatial averaging method based on adaptive weights, which can obtain high-quality pulse signals by applying different weights to facial sub-regions of interest (sub-ROIs; sROIs). First, the facial ROI is divided into seven sROIs and the coarse heart rate (HR) is calculated from them. Next, the signal-to-noise ratio (SNR) of the raw signal obtained from each sROI is calculated using the coarse HR, and then a high-quality pulse signal is obtained by assigning positive or negative weights to each sROI based on the SNRs. We compare our method with others through the quality analysis of the obtained pulse signals using the self-collected database and the public database PURE. The comparison results show that the proposed method can provide a better pulse signal compared to other methods under various resolutions and states. This proposed method can obtain the pulse signal with better quality, which is helpful to accurately measure physiological parameters, such as HR and HR variability. [ABSTRACT FROM AUTHOR]

Sign recognition is important for identifying benign and malignant nodules. This paper proposes a new sign recognition method based on image retrieval for lung nodules. First, we construct a deep learning framework to extract semantic features that can effectively represent sign information. Second, we translate the high-dimensional image features into compact binary codes with principal component analysis (PCA) and supervised hashing. Third, we retrieve similar lung nodule images with the presented adaptive-weighted similarity calculation method. Finally, we recognize nodule signs from the retrieval results, which can also provide decision support for diagnosis of lung lesions. The proposed method is validated on the publicly available databases: lung image database consortium and image database resource initiative (LIDC-IDRI) and lung computed tomography (CT) imaging signs (LISS). The experimental results demonstrate our retrieval method substantially improves retrieval performance compared with those using traditional Hamming distance, and the retrieval precision can achieve 87.29% when the length of hash code is 48 bits. The entire recognition rate on the basis of the retrieval results can achieve 93.52%. Moreover, our method is also effective for real-life diagnosis data. [ABSTRACT FROM AUTHOR]

A novel adaptive weight online sequential extreme learning machine (AWOS-ELM) is proposed for predicting time series problems based on an online sequential extreme learning machine (OS-ELM) in this paper. In real-world online applications, the sequentially coming data chunk usually possesses varying confidence coefficients, and the data chunk with a low confidence coefficient tends to mislead the subsequent training process. The proposed AWOS-ELM can improve the training process by accessing the confidence coefficient adaptively and determining the training weight accordingly. Experiments on six time series prediction data sets have verified that the AWOS-ELM algorithm performs better in generalization performance, stability, and prediction ability than the OS-ELM algorithm. In addition, a real-world mechanical system identification problem is considered to test the feasibility and efficacy of the AWOS-ELM algorithm. [ABSTRACT FROM AUTHOR]

Representation-based methods have found widespread applications in various classification tasks. However, these methods cannot deal effectively with imbalanced data scenarios. They tend to neglect the importance of minority samples, resulting in bias toward the majority class. To address this limitation, we propose a density-based discriminative nonnegative representation approach for imbalanced classification tasks. First, a new class-specific regularization term is incorporated into the framework of a nonnegative representation based classifier (NRC) to reduce the correlation between classes and improve the discrimination ability of the NRC. Second, a weight matrix is generated based on the hybrid density information of each sample’s neighbors and the decision boundary, which can assign larger weights to minority samples and thus reduce the preference for the majority class. Furthermore, the resulting model can be efficiently optimized through the alternating direction method of multipliers. Extensive experimental results demonstrate that our proposed method is superior to numerous state-of-the-art imbalanced learning methods. [ABSTRACT FROM AUTHOR]

Hyperspectral video target tracking is generally challenging when the scale of the target varies. In this paper, a novel algorithm is proposed to address the challenges prevalent in the existing hyperspectral video target tracking approaches. The proposed approach employs deep features along with spectral matching reduction and adaptive-scale 3D hog features to track the objects even when the scale is varying. Spectral matching reduction is adopted to estimate the spectral curve of the selected target region using a weighted combination of the global and local spectral curves. In addition to the deep features, adaptive-scale 3D hog features are extracted using cube-level features at three different scales. The four weak response maps thus obtained are then combined using adaptive weights to yield a strong response map. Finally, the region proposal module is utilized to estimate the target box. The proposed strategies make the approach robust against scale variations of the target. A comparative study on different hyperspectral video sequences illustrate the superior performance of the proposed algorithm as compared to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

The whale optimization algorithm is a new type of swarm intelligence bionic optimization algorithm, which has achieved good optimization results in solving continuous optimization problems. However, it has less application in discrete optimization problems. A variable neighborhood discrete whale optimization algorithm for the traveling salesman problem (TSP) is studied in this paper. The discrete code is designed first, and then the adaptive weight, Gaussian disturbance, and variable neighborhood search strategy are introduced, so that the population diversity and the global search ability of the algorithm are improved. The proposed algorithm is tested by 12 classic problems of the Traveling Salesman Problem Library (TSPLIB). Experiment results show that the proposed algorithm has better optimization performance and higher efficiency compared with other popular algorithms and relevant literature. [ABSTRACT FROM AUTHOR]

Data driven fault diagnosis has attracted a lot of attention in recent years owing to its intelligent and accurate detection of fault categories. However, it is a challenge for its applications in real world. The abundant labeled data is extremely necessary for data driven fault diagnosis to train a favorable model. Even though enough labeled data is prepared for training a model, we still cannot ensure the data used for training and testing draw from identical distribution. In other words, the labeled source domain has different distribution compared with the unlabeled target domain. In this paper, we introduce the domain adaptation strategy into deep neural networks to propose a deep domain adaptation architecture, which realizes to learn knowledge from the labeled source domain to facilitate the target classification. In the proposed model, the conditional and marginal distribution are adapted together in multiple layers of neural network, which uses MMD to measure the distribution discrepancy. Besides, the relative importance between marginal and conditional distributions is explored, and an adaptively weighted strategy is further introduced to learn the relative importance of the two distributions. To evaluate the proposed method, we conduct the simulations on different workloads, sensor deployment locations, and even different platforms. The results show the superiority of the proposed model to other intelligent fault diagnosis methods, meanwhile verify the necessity of marginal and conditional distribution adaptation and adaptive weighted strategy. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the WOA was easy to fall into local optimum and low convergence precision, this paper proposed an improved whale optimization algorithm (IWOA). The algorithm initialized the population by quasi-reverse learning methods and improved the diversity of the population. Then the algorithm modified the linear convergence factor to a nonlinear convergence factor, which was beneficial to balance the global search ability and local development ability. In addition, the algorithm improved the local search ability of the whale optimization algorithm by increasing the adaptive weight and imp roved convergence precision. Finally, the algorithm adjusted the whale optimization algorithm in time by a random differential mutation strategy to avoid falling into the local optimum. It selected nine benchmark functions in the experiment, and iterated all the algorithms 30 times. The improved whale optimization algorithm compared to the original whale optimization algorithm and five improved whale optimization algorithms, the results show that the mean and standard deviation of the algorithm are better than other algorithms, the convergence curve of the algorithm is also superior to most other algorithms. It shows that the imp roved whale optimization algorithm has the best convergence accuracy and algorithm stability, and the convergence speed is significantly faster than most other improved whale optimization algorithms. [ABSTRACT FROM AUTHOR]

Industrial processes often contain significant strong nonlinearity and time-varying behavior. Traditional ElM based soft sensor sometimes fails to make use of data information effectively and has poor prediction performance. This paper proposed an improved particle swarm optimization algorithm, which had better convergence speed and search ability than standard PSO. This algorithm used the characteristics of Gaussian distribution to update the inertia weight adaptively and changed learning factor linearly. It optimized the penalty coefficient and kernel parameter of ELM to obtain a group of optimal parameters. This algorithm was applied to soft sensor modeling for the debutanizer column process. The simulation results verify that the proposed method has good prediction accuracy and generalization performance. [ABSTRACT FROM AUTHOR]

The current constraint rules of end-to-end infrared and visible image fusion (IVIF) networks based on deep learning solely focus on the pixel level, disregarding the consideration of deep features and global information. To address this limitation, this paper proposes an multi-level adaptive perception-guided image fusion approach, named MAPFusion. The main idea is to design a specific network structure and use features to guide the training of the network. Specifically, on the one hand, a new loss function strategy is designed, which combines pixel-level, structure-level, and feature-level strategies to comprehensively enhance the information of the fused image. In particular, the multi-level adaptive perceptual loss is introduced as a feature-level strategy, which preserves both low-level positional data and high-level semantic data by constraining the original image and fused image features. Moreover, adaptive weights are constructed using the information measure between feature maps, which measure the degree of information preservation of different source images. On the other hand, a new fusion network is proposed, which uses the improved U-Net structure to extract the multi-scale features of the image, and adds the Atrous Spatial Pyramid Pooling (ASPP) to the specific network layer, which can increase the receptive field and effectively take advantage of the global information of the image. Comparative experiments demonstrate that the proposed method effectively utilizes the information existing in infrared and visible images, resulting in superior visual quality and objective evaluation compared to SOTA algorithms. Ablation and supplementary experiments further validate the rationality of the proposed method and its potential for advanced vision tasks. • The U-Net network structure combined with ASPP simultaneously captures the global and multi-scale feature. • Compared with the pixel-level loss, the feature-level loss can preserve the semantic features of the original image. • The adaptive weights make the fusion function adaptively measure the importance of infrared and visible images. • A large number of experiments prove the rationality and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Cloud Manufacturing (CMfg) has attracted lots of attention from scholars and practitioners. The purpose of quality of service (QoS)-aware manufacturing cloud service composition (MCSC), as one of the key issues in CMfg, is to combine different available manufacturing cloud services (MCSs) to generate an optimized MCSC that can meet the diverse requirements of customers. However, many available MCSs, deployed in the CMfg platform, have the same function but different QoS attributes. It is a great challenge to achieve optimal MCSC with a high QoS. In order to obtain better optimization results efficiently for the QoS-MCSC problems, a whale optimization algorithm (WOA) with adaptive weight, Lévy flight, and adaptive crossover strategies (ASWOA) is proposed. In the proposed ASWOA, adaptive crossover inspired by the genetic algorithm is developed to balance exploration and exploitation. The Lévy flight is designed to expand the search space of the WOA and accelerate the convergence of the WOA with adaptive crossover. The adaptive weight is developed to extend the search scale of the exploitation. Simulation and comparison experiments are conducted on various benchmark functions and different scale QoS-MCSC problems. The QoS attributes of the problems are randomly and symmetrically generated. The experimental results demonstrate that the proposed ASWOA outperforms other compared cutting-edge algorithms. [ABSTRACT FROM AUTHOR]

To realize aerial target recognition in a complex environment, we propose a multi-source Takagi–Sugeno (T-S) intuitionistic fuzzy rules method (MTS-IFRM). In the proposed method, to improve the robustness of the training process of the model, the features of the aerial targets are classified as the input results of the corresponding T-S target recognition model. The intuitionistic fuzzy approach and ridge regression method are used in the consequent identification, which constructs a regression model. To train the premise parameter and reduce the influence of data noise, novel intuitionistic fuzzy C-regression clustering based on dynamic optimization is proposed. Moreover, a modified adaptive weight algorithm is presented to obtain the final outputs, which improves the classification accuracy of the corresponding model. Finally, the experimental results show that the proposed method can effectively recognize the typical aerial targets in error-free and error-prone environments, and that its performance is better than other methods proposed for aerial target recognition. [ABSTRACT FROM AUTHOR]

In this paper, we propose a joint collaborative representation (CR) classification method with multitask learning for hyperspectral imagery. The proposed approach consists of the following aspects. First, several complementary features are extracted from the hyperspectral image. We next apply these features into the unified multitask-learning-based CR framework to acquire a representation vector and adaptive weight for each feature. Finally, the contextual neighborhood information of the image is incorporated into each feature to further improve the classification performance. The experimental results suggest that the proposed algorithm obtains a competitive performance and outperforms other state-of-the-art regression-based classifiers and the classical support vector machine classifier. [ABSTRACT FROM PUBLISHER]

Abstract The goal of super-resolution (SR) is to recover a high-resolution (HR) image from its corresponding low-resolution (LR) image. It is an ill-posed problem. Most recent methods are based on external training data. They can reconstruct pleasing HR results, especially when the input patch has a similar counterpart within the training dataset. Other methods are driven by self-similarity and are called internal methods. They can produce visually plausible HR images when the input images contain abundant regular structures. In this paper, we propose a hybrid method for image SR that exploits the complementary advantages of external and internal SR methods. Each input LR patch is first super-resolved using convolutional neural network (CNN) for external SR and self-similarity for internal SR. Then, we calculate the perceptual similarity between the feature representations from the pre-trained VGG network to learn an adaptive weight. Finally, our algorithm automatically selects the optimal method on the basis of the calculated adaptive weight. The experimental results of our visual and quantitative evaluations verify the effectiveness of the proposed method, by comparing it with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Discriminative correlation filter (DCF) based tracking algorithms have recently shown impressive performance on benchmark datasets. However, amount of recent researches are vulnerable to heavy occlusions, irregular deformations and so on. In this paper, we intend to solve these problems and handle the contradiction between accuracy and real-time in the framework of tracking-by-detection. Firstly, we propose an innovative strategy to combine the template and color-based models instead of a simple linear superposition and rely on the strengths of both to promote the accuracy. Secondly, to enhance the discriminative power of the learned template model, the spatial regularization is introduced in the learning stage to penalize the objective boundary information corresponding to features in the background. Thirdly, we utilize a discriminative multi-scale estimate method to solve the problem of scale variations. Finally, we research strategies to limit the computational complexity of our tracker. Abundant experiments demonstrate that our tracker performs superiorly against several advanced algorithms on both the OTB2013 and OTB2015 datasets while maintaining the high frame rates. [ABSTRACT FROM AUTHOR]

Direct performance predictive control is the most cutting-edge research in aero-engine control. The existing subspace-based improved model predictive control (SIMPC) effectively handled the problem of difficulty solving the prediction model in predictive control. However, the strong nonlinearity of aero-engine makes the controller with design parameters set constant invariant value unable to guarantee consistent control effect in all states. Even with general scheduling for design parameters, the controller's performance still behaves poorly. Therefore, this paper innovatively proposes an adaptive tuning method for the design parameters of the SIMPC controller to adapt to all engine states. Firstly, by analyzing the influence of each design parameter of the controller on the control effect, the tracking weight with strong sensitivity is selected as the dynamic tuning parameter. Then, three variables of the ratio of PLA angle, relative tracking error, and scale factor are successfully introduced to map the tracking weight value without adding additional design parameters. Thus, a fuzzy logic tuner based on these variables is then designed for adaptively tuning the tracking weight to maintain the controller's performance. Finally, results show that, compared with the existing methods, while keeping the maximum dynamic response performance, the proposed method eliminates the phenomenon of large overshoot and controls it within 2% required in the whole state range. Compared with the general scheduling method, the designed adaptive tracking weight with positive excitation caused by relative tracking error effectively shortens the response time, especially with an average performance improvement of 17% under small step changes. Whether the engine is in standard or fault conditions, the designed adaptive tracking weight is effective and feasible for undertaking the controller's consistent control effects in all states. [ABSTRACT FROM AUTHOR]