The multimodal named entity recognition task on social media involves recognizing named entities with textual and visual information, which is of great significance for information processing. Nevertheless, many exist...
详细信息
The multimodal named entity recognition task on social media involves recognizing named entities with textual and visual information, which is of great significance for information processing. Nevertheless, many existing models still face the following challenges. First, in the process of cross-modal interaction, the attention mechanism sometimes focuses on trivial parts in the images that are not relevant to entities, which not only neglects valuable information but also inevitably introduces visual noise. Second, the gate mechanism is widely used for filtering out visual information to reduce the influence of noise on text understanding. However, the gate mechanism neglects capturing fine-grained semantic relevance between modalities, which easily affects the filtration process. To address these issues, we propose a cross-modal integration framework based on the surprisingly popular algorithm, aiming at enhancing the integration of effective visual guidance and reducing the interference of irrelevant visual noise. Specifically, we design a dual-branch interaction module that includes the attention mechanism and the surprisingly popular algorithm, allowing the model to focus on valuable but overlooked parts in the images. Furthermore, we compute the matching degree between modalities at the multi-granularity level, using the Choquet integral to establish amore reasonable basis for filtering out visual noise. We have conducted extensive experiments on public datasets, and the experimental results demonstrate the advantages of our model.
While many Particle Swarm Optimization (PSO) algorithms only use fitness to assess the performance of particles, in this work, we adopt surprisingly popular algorithm (SPA) as a complementary metric in addition to fit...
详细信息
While many Particle Swarm Optimization (PSO) algorithms only use fitness to assess the performance of particles, in this work, we adopt surprisingly popular algorithm (SPA) as a complementary metric in addition to fitness. Consequently, particles that are not widely known also have the opportunity to be selected as the learning exemplars. In addition, we propose a Euclidean distance-based adaptive topology to cooperate with SPA, where each particle only connects to k number of particles with the shortest Euclidean distance during each iteration. We also introduce the adaptive topology into heterogeneous populations to better solve large-scale problems. Specifically, the exploration sub-population better preserves the diversity of the population while the exploitation sub-population achieves fast convergence. Therefore, large-scale problems can be solved in a collaborative manner to elevate the overall performance. To evaluate the performance of our method, we conduct extensive experiments on various optimization problems, including three benchmark suites and two real-world optimization problems. The results demonstrate that our Euclidean distance-based adaptive topology outperforms the other widely adopted topologies and further suggest that our method performs significantly better than state-of-the-art PSO variants on small, medium, and large-scale problems.
This paper considers the impact of setup time in production scheduling and proposes energy-aware distributed hybrid flow shop scheduling problem with sequence-dependent setup time(EADHFSP-ST)that simultaneously optimi...
详细信息
This paper considers the impact of setup time in production scheduling and proposes energy-aware distributed hybrid flow shop scheduling problem with sequence-dependent setup time(EADHFSP-ST)that simultaneously optimizes the makespan and the energy *** develop a mixed integer linear programming model to describe this problem and present a two-stage adaptive memetic algorithm(TAMA)with a surprisinglypopular ***,a hybrid initialization strategy is designed based on the two optimization objectives to ensure the convergence and diversity of ***,multiple population co-evolutionary approaches are proposed for global search to escape from traditional cross-randomization and to balance exploration and ***,considering that the memetic algorithm(MA)framework is less efficient due to the randomness in the selection of local search operators,TAMA is proposed to balance the local and global *** first stage accumulates more experience for updating the surprisingly popular algorithm(SPA)model to guide the second stage operator selection and ensures population *** second stage gets rid of local optimization and designs an elite archive to ensure population ***,five problem-specific operators are designed,and non-critical path deceleration and right-shift strategies are designed for energy ***,to evaluate the performance of the proposed algorithm,multiple experiments are performed on a benchmark with 45 *** experimental results show that the proposed TAMA can solve the problem effectively.
Most existing studies on distributed permutation flow shop scheduling assume identical shops, overlooking the impact of heterogeneous shops. This paper addresses the energy-efficient distributed heterogeneous permutat...
详细信息
Most existing studies on distributed permutation flow shop scheduling assume identical shops, overlooking the impact of heterogeneous shops. This paper addresses the energy-efficient distributed heterogeneous permutation flow shop scheduling problem, which accounts for variations in energy consumption when jobs are processed on different machines in heterogeneous factories. Several research gaps are stated following: (1) Previous studies predominantly use the NEH algorithm and its variants, which require substantial computational resources, while a single random initialization strategy fail to generate a high-quality population. (2) The classical Jaya algorithm relies on a single learning target, which may lead the population to converge prematurely to local optima. (3) Confidence-based operator selection models are influenced by historical performance and cannot dynamically adjust operator weights based on recent performance. (4) The previous works lack of effective energy-saving strategies. To address these issues, we propose a competitive multilevel Jaya algorithm with SPA-based multi-directional local search (CMJA-SPALS). Key innovations of CMJA-SPALS as follows: (1) A hybrid initialization strategy that generates a high-quality initial population with good diversity and convergence using fewer evaluations. (2) The multilevel competition mechanism uses non-dominated sorting to divide the population into multiple levels. Individuals within the same level are randomly paired for competition to determine diversified learning targets, significantly enhancing population diversity and reducing the risk of converging to local optima. (3) Individuals apply specific search operators based on its optimization bias, while the surprisingly popular algorithm (SPA) dynamically adjusts the selection probabilities of operators, improving local search success rates and accelerating convergence. (4) A critical path-based energy-saving strategy designed to reduce machine idle time
This dissertation presents a big-picture view for policymakers and related stakeholders regarding the future development of car sharing services. Car sharing has the potential to significantly disrupt the personal mob...
详细信息
This dissertation presents a big-picture view for policymakers and related stakeholders regarding the future development of car sharing services. Car sharing has the potential to significantly disrupt the personal mobility market, particularly on the dawn of self-driving cars. Thus, understanding car sharing service s market penetration and implications are urgently needed. Previous studies in this domain have predominantly focused on the views, opinions, and preferences of consumers. In this dissertation, both opinions from experts and consumers are used. Firstly, an expert elicitation and aggregation technique that relies on transport experts opinions is adopted to investigate the role of car sharing in the future. Specifically, based on the opinions of transport experts, this research elicits experts judgement from across government, industry, and academia to gain insights into the future of car sharing markets in four countries: Australia, Malaysia, Indonesia, and Thailand. In addition, a well-designed stated preference survey based on respondents real trip information is implemented to solicit general public s preferences towards car sharing services in Australia. Nested logit model and random parameter multinomial logit model are employed to analysis the SP data. More specifically, the impacts of self- driving capability of car sharing (or shared autonomous vehicles, SAVs) on respondents iii vehicle ownership choices and trip mode choices that were seldom studied in the literature are investigated. The analysis reveals that from a mobility supplier perspective, energy and vehicle prices are not associated with future adoption of car sharing. The results also show that the more knowledgeable an expert is, the more pessimistic they are about the market penetration of car sharing in 2016, and the more optimistic they are about the prevalence of car sharing in 2030. Looking at the consumer side, inconsistent with the prior studies, the results of this research sho
暂无评论