查看更多>>摘要：? 2022 Elsevier Inc.Poor observation conditions, such as haze, fog, offgas, and dust, which result in contrast degradation and colour distortion issues, negatively affect remote sensing images (RSIs). In this study, the local patchwise minimal values prior (MinVP) and local patchwise maximal values prior (MaxVP) are proposed for single RSI dehazing. As alternatives to the classical dark channel prior (DCP) and bright channel prior (BCP), the feasibility and reliability of MinVP and MaxVP are investigated. The transmission maps from MinVP and MaxVP are approximately equivalent to those from DCP and BCP but more efficient. To address the common problems of halo, oversaturation, and overexposure phenomena in dehazing processes, a dehazing method based on MinVP (named MinVPM) is proposed. The refined atmospheric light map and compensated transmission map are derived and formulated according to the atmospheric scattering model (ASM). Moreover, to improve the contrast in the dehazed images by MinVPM, a simple enhancement method based on MaxVP (named MaxVPM) is proposed, the formulae of which are analogously derived to those of MinVPM. The upgraded dehazing version of MinVPM, named EVPM, is the combination of MinVPM and MaxVPM. Extensive experiments and corresponding evaluations demonstrate that the proposed MinVPM and EVPM can achieve satisfactory results and high computational efficiency and outperform state-of-the-art dehazing methods for remote sensing image dehazing.
查看更多>>摘要：? 2022 Elsevier Inc.Due to the differences of observation equipment and technical means, the size of the color digital image is not the same. In addition, most of digital watermarking methods used to protect the copyright of color digital images have weak robustness against geometric attacks. Therefore, this paper proposes a robust adaptive blind watermarking method to protect the copyright of color digital images. In the proposed method, the frequency domain characteristics of Slant transform are used to directly calculate the maximum energy coefficient of the pixel block, the maximum element of the coefficient matrix obtained after Slant transform in the spatial domain, and the color digital watermark is embedded by quantifying the maximum energy coefficient. At the same time, the adaptive strategies, which including the adaptive image size, the adaptive quantization step, the adaptive watermark encoding and the adaptive watermark embedding position, are proposed in this paper. Moreover, the proposed method can use geometric features of the image to correct many attacked images. Compared with the state-of-the-art watermarking methods, the proposed method can achieve acceptable imperceptibility and has larger watermark capacity, stronger robustness, higher security and better real-time performance.
查看更多>>摘要：? 2022 Elsevier Inc.Structural health monitoring (SHM) is extremely vital for the diagnosis and prognosis of civil structures. As an important part of the SHM system, vibration-based damage detection (VBDD) methods have become a research hotspot with the development of sensor technologies. These methods are utilized to assess structural conditions or localize and classify damages. Recently end-to-end deep learning architectures have been widely used in VBDD tasks and achieved state-of-the-art results. However, there are seldom investigations on the attention mechanism in VBDD, which has been demonstrated as an effective module to extract features in other domains. In this paper, we propose a channel-spatial-temporal attention-based network to refine and enrich the discriminative sample-specific features in three dimensions, namely, channel, space, and time simultaneously. Specifically, the local and global block we designed is to extract the local and global spatial features adaptively, and the grouped self-attention is presented to extract the long- and short-term temporal features. Moreover, the squeeze-and-excitation block is selected to emphasize vital channels. Extensive experiments are conducted on three-span continuous rigid frame bridge scale model and IASC-ASCE benchmark datasets, and the results prove that the proposed method is superior to the existing state-of-the-art methods.
查看更多>>摘要：? 2022 Elsevier Inc.The rapid development of location-based services spurred a large number of user-centric applications. Particularly, an interesting topic has attracted the attention of researchers that is to link trajectories to users (TUL). Despite the significant progress made by recent deep learning-based human mobility learning models, tackling TUL problem is still challenging. In this paper, we propose a novel reinforced trajectory learning approach called GraphTUL that implements an adversarial network with the policy gradient to improve the identification ability and leverages both labeled and unlabeled trajectories to address the insufficient label issue in a semi-supervised manner. Besides, some critical factors related to personal context and indispensable elements in current mobility learning models are still missing. Thus, we propose a novel graph-based human motion representation model (CGE) to exploit the contextual information from users’ trajectories for alleviating data sparsity and contextual constraint issues. CGE builds a unified graph with historical check-ins to reflect users’ geographical preferences and visiting intentions. It allows us to sample synthetic but realistic trajectories for augmenting data and enhancing contextual check-in embedding. We also successfully apply it to next check-in prediction task. The experimental results conducted on several real-world datasets demonstrate that our proposed method achieves significantly better performance than the state-of-the-art baselines.
Pasquadibisceglie V.Appice A.Castellano G.van der Aalst W....
22页
查看更多>>摘要：? 2022 Elsevier Inc.Process discovery, one of the main branches of process mining, aims to discover a process model that accurately describes the underlying process captured within the event data recorded in an event log. In general, process discovery algorithms return models describing the entire event log. However, this strategy may lead to discover complex, incomprehensible process models concealing the correct and/or relevant behavior of the underlying process. Processing the entire event log is no longer feasible when dealing with large amounts of events. In this study, we propose the PROMISE+ method that rests on an abstraction involving predictive process mining to generate an event log summary. This summarization step may enable the discovery of simpler process models with higher precision. Experiments with several benchmark event logs and various process discovery algorithms show the effectiveness of the proposed method.
查看更多>>摘要：? 2022 Elsevier Inc.To comprehensively enhance the robust tracking performance, a leader–follower Stackelberg game oriented adaptive robust constraint-following control scheme has been proposed for a class of uncertain mechanical systems. In the proposed scheme, a fuzzy set-theoretic description represents the uncertainties (possibly fast time-varying), and an adaptive robust constraint-following control ensures the robust stability. With the fuzzy uncertainty description and control performance analysis, a leader–follower game theory is employed to obtain multiple optimal gains for the proposed control scheme. Further, the existence of these optimal parameters can be verified. The proposed approach is successfully applied to a lower limb exoskeleton (LLE) robot system for rehabilitation training.
查看更多>>摘要：? 2022 Elsevier Inc.Convolutional neural networks (CNNs) have achieved extraordinary success on many image classification tasks in recent years. The use of dilated convolution in a CNN can increase the network's receptive field and improve its performance, and dilated convolution can also be used to compress a CNN to realize a lightweight model. In previous studies, multiscale dilated convolution has been adopted with a focus on improving the internal network structure of a specific CNN model. Because they enable the direct use of pretrained models, transfer learning CNNs (TL-CNNs) have been widely applied for image recognition based on small datasets. This paper proposes a novel multiscale dilated-convolution-based ensemble learning (MDCEL) method for effectively improving the performance of a pretrained CNN model. The authors' primary assumption is that semantic representations of different images can be obtained based on multiscale dilated convolution. Therefore, constructing an ensemble of diverse TL-CNN classifiers makes it possible to achieve higher performance than that offered by the traditional TL-CNN methods. The MDCEL method is highly versatile and can be applied to various conventional pretrained CNN models and lightweight CNN models. Moreover, this method does not require the modification of the internal structures of the pretrained CNN models and has high training efficiency. Experimental results on three public image classification datasets demonstrate that the proposed method outperforms the baseline traditional TL-CNN method. Compared with the baseline approach, the MDCEL approach improves the accuracy and F1 values by nearly 1–4%. In addition, an experiment on a real case dataset obtained from a manufacturing enterprise further proves the practicability of the proposed method.
查看更多>>摘要：? 2022 Elsevier Inc.Despite the Video Violence Detection (VVD) plays a critical role in video surveillance, it is not trivial in crowded scenes due to the complexity and diversity of violence. Generally, the most typical features of violence are its drastic, disordered, and chaotic motion in contrast to non-violence. To capture these features for violence analysis in a video clip, we propose a novel Angle-level Co-occurrence Matrix (ALCM). Given a video volume, we treat it as a tensor of rank 3, which consists of a bound of fibers in one plane. ALCM records the co-occurrence of two specific quantized angle levels between fibers with their neighbors, which is the distribution of the co-occurrence of fiber pairs with specific similarities in one plane of the tensor of rank 3. To completely characterize the violence in the volume, we compute three ALCMs for three orthogonal planes to form a TOP-ALCM, respectively. We also propose both conventional and deep-learning-based VVD frameworks, in which the former one leverages the features such as entropy, homogeneity, and energy computed from TOP-ALCM for classification, while the latter one directly uses CNN to classify the TOP-ALCMs. Experimental results analysis demonstrates that the proposed TOP-ALCM outperforms the state-of-the-art methods for VVD.
查看更多>>摘要：? 2022 Elsevier Inc.Dynamic multiobjective optimization problems (DMOPs) require the robust tracking of Pareto-optima varying over time. Previous transfer learning-based problem solvers consume the most time on complex training of transfer model or applying a plenty of evaluations to find transferred individuals, decreasing computational efficiency. To address this issue, a domain adaptation learning strategy based dynamic multiobjective evolutionary algorithm is proposed in this paper. The mapping matrix learned by subspace distribution alignment (SDA) is utilized to transform the search space between last and current environments for promoting efficient knowledge transfer. Especially, the process of constructing mapping is derived from the simpler calculation, saving computational cost. Based on this model, transferred individuals are generated from a part of historical optima at last time. Additionally, an increment information is defined as the difference between center points of POSs in past two environments, and employed to produce a noise obeying uniform distribution. After adding it on a temporary population consisting of transferred individuals and the rest historical optima, an initial population with good diversity under new environment is formed. Experimental results on 12 benchmark functions indicate that the proposed method outperforms the other six state-of-the-art comparative ones, achieving the promising performance in solving DMOPs.
查看更多>>摘要：? 2022 Elsevier Inc.In order to further improve the performance of L-SHADE, one of the most competitive variants of differential evolution (DE), a novel adaptive L-SHADE algorithm named AL-SHADE is proposed in the study. Two main parts have been modified for L-SHADE. In one part, a novel mutation strategy current-to-Amean/1 is added to the mutation process to improve the exploitation ability and make full use of population information. In another part, a selection strategy with adaptation scheme for mutation strategies is proposed to tune the exploitation and exploration. The performance of AL-SHADE is evaluated using CEC 2018 and CEC 2014 test suites comparing with L-SHADE, and its state-of-the-art variants, i.e., DbL-SHADE, EB-LSHADE, ELSHADE-SPACMA, jSO, and mL-SHADE. The statistical results demonstrate that AL-SHADE outperforms other competitors in terms of convergence efficiency and accuracy. Finally, AL-SHADE is applied to solve the problem of UAV swarm resource configuration, and the promising performance of AL-SHADE for solving constrained optimization problem are demonstrated by the experimental results. The source code of AL-SHADE can be downloaded from https://github.com/Yintong-Li/AL-SHADE.
NSTL
Elsevier