In this article, a novel dynamic multiobjective optimization algorithm (DMOA) is proposed based on a designed hierarchical response system (HRS). Named HRS-DMOA, the proposed algorithm mainly aims at integrating merits from the mainstream ideas of dynamic behavior handling (i.e., the diversity-, memory-, and prediction-based methods) in order to make flexible responses to environmental changes. In particular, by two predefined thresholds, the environmental changes are quantified as three levels. In case of a slight environmental change, the previous Pareto set-based refinement strategy is recommended, while the diversity-based reinitialization method is applied in case of a dramatic environmental change. For changes occurring at a medium level, the transfer-learning-based response is adopted to make full use of the historical searching experiences. The proposed HRS-DMOA is comprehensively evaluated on a series of benchmark functions, and the results show an improved comprehensive performance as compared with four popular baseline DMOAs in terms of both convergence and diversity, which also outperforms other two state-of-the-art DMOAs in ten out of 14 testing cases, exhibiting the competitiveness and superiority of the algorithm. Finally, extensive ablation studies are carried out, and from the results, it is found that as compared with randomly selecting the response methods, the proposed HRS enables more reasonable and efficient responses in most cases. In addition, the generalization ability of the proposed HRS as a flexible plug-and-play module to handle dynamic behaviors is proven as well.

In this article, a novel dynamic multiobjective optimization algorithm (DMOA) with a cascaded fuzzy system (CFS) is developed, which aims to promote objective knowledge transfer from an innovative perspective of comprehensive information characterization. This development seeks to overcome the bottleneck of negative transfer in evolutionary transfer optimization (ETO)-based algorithms. Specifically, previous Pareto solutions, center- and knee-points of multisubpopulation are adaptively selected to establish the source domain, which are then assigned soft labels through the designed CFS, based on a thorough evaluation of both convergence and diversity. A target domain is constructed by centroid feed-forward of multisubpopulation, enabling further estimations on learning samples with the assistance of the kernel mean matching (KMM) method. By doing so, the property of nonindependently identically distributed data is considered to enhance efficient knowledge transfer. Extensive evaluation results demonstrate the reliability and superiority of the proposed CFS-DMOA in solving dynamic multiobjective optimization problems, showing significant competitiveness in terms of mitigating negative transfer as compared to other state-of-the-art ETO-based DMOAs. Moreover, the effectiveness of the soft labels provided by CFS in breaking the “either/or” limitation of hard labels is validated, facilitating a more flexible and comprehensive characterization of historical information, thereby promoting objective and effective knowledge transfer.

Multimedia images have become an important way for the sharing of digital information. However, advanced editing tools provide easy methods for malicious content modification, resulting in less viable information. Therefore, there is an urgent need to design an algorithm for image tampering detection and localization, which is capable of locating the authenticity region of the received image, thus delivering the accurate information and assisting in correct decision making in industries and other fields. In this article, a novel dual-pathway multiscale network (DPMSN) is proposed for the image forgery detection, which mainly focuses on extracting the edge information. In particular, a dual-pathway structure is deployed to align visual features in red, green and blue (RGB) space and edge information in LAB space, where a coarse prediction mask is generated to promote accurate localization of the forged regions. By applying the variation convolution operators, comprehensive attention can be paid to various forged regions in multiple sizes. Moreover, in the multiscale fusion module, features at different stages and other low-level information are sufficiently fused to realize a robust presentation of the forged regions. Experimental results show the effectiveness of DPMSN as compared with other state-of-the-art image forgery detection models and the great robustness when facing image attacks, which means DPMSN is a trustworthy forgery detection approach in the industrial field.

In this article, a novel multi-strategy adaptive selection-based dynamic multiobjective optimization algorithm (MSAS-DMOA) is proposed, which adopts the non-inductive transfer learning (TL) paradigm to solve dynamic multiobjective optimization problems (DMOPs). In particular, based on a scoring system that evaluates environmental changes, the source domain is adaptively constructed with several optional groups to enrich the knowledge. Along with a group of guide solutions, the importance of historical experiences is estimated via the kernel mean matching (KMM) method, which avoids designing strategies to label individuals. The proposed MSAS-DMOA is comprehensively evaluated on 14 DMOPs, and the results show an overwhelming performance improvement in terms of both convergence and diversity as compared with other four popular DMOAs. In addition, ablation studies are also conducted to validate the superiority of the applied strategies in MSAS-DMOA, which can effectively alleviate the negative transfer phenomenon. Without the conventional labeling procedure, the proposed method also yields satisfactory results, which can provide valuable reference for designing other evolutionary transfer optimization (ETO) algorithms.