Journal Articles
Permanent URI for this collectionhttps://mro.massey.ac.nz/handle/10179/7915
Browse
12 results
Search Results
Item Evolutionary Optimization of Energy Consumption and Makespan of Workflow Execution in Clouds(MDPI (Basel, Switzerland), 2023-04-30) Xing L; Li J; Cai Z; Hou F; Sanz JAMaking sound trade-offs between the energy consumption and the makespan of workflow execution in cloud platforms remains a significant but challenging issue. So far, some works balance workflows’ energy consumption and makespan by adopting multi-objective evolutionary algorithms, but they often regard this as a black-box problem, resulting in the low efficiency of the evolutionary search. To compensate for the shortcomings of existing works, this paper mathematically formulates the cloud workflow scheduling for an infrastructure-as-a-service (IaaS) platform as a multi-objective optimization problem. Then, this paper tailors a knowledge-driven energy- and makespan-aware workflow scheduling algorithm, namely EMWSA. Specifically, a critical task adjustment-based local search strategy is proposed to intelligently adjust some critical tasks to the same resource of their successor tasks, striving to simultaneously reduce workflows’ energy consumption and makespan. Further, an idle gap reuse strategy is proposed to search the optimal energy consumption of each non-critical task without affecting the operation of other tasks, so as to further reduce energy consumption. Finally, in the context of real-world workflows and cloud platforms, we carry out comparative experiments to verify the superiority of the proposed EMWSA by significantly outperforming 4 representative baselines on 19 out of 20 workflow instances.Item Decision variable contribution based adaptive mechanism for evolutionary multi-objective cloud workflow scheduling(Springer Nature, 2023-06-29) Li J; Xing L; Zhong W; Cai Z; Hou FWorkflow scheduling is vital to simultaneously minimize execution cost and makespan for cloud platforms since data dependencies among large-scale workflow tasks and cloud workflow scheduling problem involve large-scale interactive decision variables. So far, the cooperative coevolution approach poses competitive superiority in resolving large-scale problems by transforming the original problems into a series of small-scale subproblems. However, the static transformation mechanisms cannot separate interactive decision variables, whereas the random transformation mechanisms encounter low efficiency. To tackle these issues, this paper suggests a decision-variable-contribution-based adaptive evolutionary cloud workflow scheduling approach (VCAES for short). To be specific, the VCAES includes a new estimation method to quantify the contribution of each decision variable to the population advancement in terms of both convergence and diversity, and dynamically classifies the decision variables according to their contributions during the previous iterations. Moreover, the VCAES includes a mechanism to adaptively allocate evolution opportunities to each constructed group of decision variables. Thus, the decision variables with a strong impact on population advancement are assigned more evolution opportunities to accelerate population to approximate the Pareto-optimal fronts. To verify the effectiveness of the proposed VCAES, we carry out extensive numerical experiments on real-world workflows and cloud platforms to compare it with four representative algorithms. The numerical results demonstrate the superiority of the VCAES in resolving cloud workflow scheduling problems.Item TFGNet: Frequency-guided saliency detection for complex scenes(Elsevier B.V., 2025-01-08) Wang Y; Wang R; Liu J; Xu R; Wang T; Hou F; Liu B; Lei NSalient object detection (SOD) with accurate boundaries in complex and chaotic natural or social scenes remains a significant challenge. Many edge-aware or/and two-branch models rely on exchanging global and local information between multistage features, which can propagate errors and lead to incorrect predictions. To address this issue, this work explores the fundamental problems in current U-Net architecture-based SOD models from the perspective of image spatial frequency decomposition and synthesis. A concise and efficient Frequency-Guided Network (TFGNet) is proposed that simultaneously learns the boundary details (high-spatial frequency) and inner regions (low-spatial frequency) of salient regions in two separate branches. Each branch utilizes a Multiscale Frequency Feature Enhancement (FFE) module to learn pixel-wise frequency features and a Transformer-based decoder to learn mask-wise frequency features, improving a comprehensive understanding of salient regions. TFGNet eliminates the need to exchange global and local features at intermediate layers of the two branches, thereby reducing interference from erroneous information. A hybrid loss function is also proposed to combine BCE, IoU, and Histogram dissimilarity to ensure pixel accuracy, structural integrity, and frequency distribution consistency between ground truth and predicted saliency maps. Comprehensive evaluations have been conducted on five widely used SOD datasets and one underwater SOD dataset, demonstrating the superior performance of TFGNet compared to state-of-the-art methods. The codes and results are available at https://github.com/yiwangtz/TFGNet.Item A Two-State Dynamic Decomposition-Based Evolutionary Algorithm for Handling Many-Objective Optimization Problems(MDPI (Basel, Switzerland), 2023-01-17) Xing L; Li J; Cai Z; Hou F; Pan L; Cui Z; Garg HDecomposition-based many-objective evolutionary algorithms (D-MaOEAs) are brilliant at keeping population diversity for predefined reference vectors or points. However, studies indicate that the performance of an D-MaOEA strongly depends on the similarity between the shape of the reference vectors (points) and that of the PF (a set of Pareto-optimal solutions symbolizing balance among objectives of many-objective optimization problems) of the many-objective problem (MaOP). Generally, MaOPs with expected PFs are not realistic. Consequently, the inevitable weak similarity results in many inactive subspaces, creating huge difficulties for maintaining diversity. To address these issues, we propose a two-state method to judge the decomposition status according to the number of inactive reference vectors. Then, two novel reference vector adjustment strategies, set as parts of the environmental selection approach, are tailored for the two states to delete inactive reference vectors and add new active reference vectors, respectively, in order to ensure that the reference vectors are as close as possible to the PF of the optimization problem. Based on the above strategies and an efficient convergence performance indicator, an active reference vector-based two-state dynamic decomposition-base MaOEA, referred to as ART-DMaOEA, is developed in this paper. Extensive experiments were conducted on ART-DMaOEA and five state-of-the-art MaOEAs on MaF1-MaF9 and WFG1-WFG9, and the comparative results show that ART-DMaOEA has the most competitive overall performance.Item The dominance of Ligularia spp. related to significant changes in soil microenvironment(Elsevier B.V., 2021-09-09) Ade L; Millner JP; Hou FExploring how plants adapt to and change the surrounding environment has become essential to understanding their survival strategies and co-evolution mechanisms. Ligularia virgaurea and Ligularia sagitta are the two most common species in the alpine grazing ecosystems of the eastern Qinghai-Tibetan Plateau (QTP) and becoming increasingly dominant. Studies have suggested that overgrazing has allowed Ligularia to gain a competitive advantage by changing plant community structure, which is often closely related to the soil environment. However, we don't fully understand the soil environment changes during this process, and the underlying mechanisms have not been explored. Therefore, we investigated plant community characteristics, soil fertility and soil microbial diversity in the L. virgaurea and L. sagitta communities on the eastern QTP. Ligularia spp. significantly changed the plant community by reducing biomass, vegetation coverage, abundance, and biodiversity, and the effect of L. sagitta on the plant community was stronger than that of L. virgaurea. In the plant communities dominated by L. virgaurea and L. sagitta, soil nutrients and soil microbial communities changed significantly. Aggregated boosted trees analysis revealed that soil Mg levels had the greatest relative influence on the structure and diversity of the soil microbial community. Our study provides data and a theoretical basis for revealing the survival strategies of L. sagitta and L. virgaurea and, provides a basis for weed management in grazed ecosystems.Item Understanding consumers' continuance intention to watch streams: A value-based continuance intention model(Frontiers Media S.A., 2023-03-01) Jia X; Pang Y; Huang B; Hou F; Xie TINTRODUCTION: Live stream-watching has become increasingly popular worldwide. Consumers are found to watch streams in a continuous manner. Despite its popularity, there has been limited research investigating why consumers continue to watch streams. Previously, the expectation-confirmation theory (ECT) has been widely adopted to explain users' continuance intention. However, most current ECT-based models are theoretically incomplete, since they only consider the importance of perceived benefits without considering users' costs and sacrifices. In this paper, we propose a value-based continuance intention model (called V-ECM), and use it to investigate factors influencing consumers' continuance intention to watch streams. METHODS: Our hypotheses were tested using an online survey of 1,220 consumers with continuance stream-watching experiences. RESULTS: Results indicate that perceived value, a process of an overall assessment between users' perceived benefits and perceived sacrifices, is proved to be a better variable than perceived benefits in determining consumers' continuance watching intention. Also, compared with other ECT-based models, V-ECM is a more comprehensive model to explain and predict consumers' continuance intention. DISCUSSION: V-ECM theoretically extends ECT-based studies, and it has potential to explain and predict other continuance intentions in online or technology-related contexts. In addition, this paper also discusses practical implications for live streaming platforms with regards to their design, functions and marketing.Item Learning and integration of adaptive hybrid graph structures for multivariate time series forecasting(Elsevier Inc., 2023-11-01) Guo T; Hou F; Pang Y; Jia X; Wang Z; Wang RRecent status-of-the-art methods for multivariate time series forecasting can be categorized into graph-based approach and global-local approach. The former approach uses graphs to represent the dependencies among variables and apply graph neural networks to the forecasting problem. The latter approach decomposes the matrix of multivariate time series into global components and local components to capture the shared information across variables. However, both approaches cannot capture the propagation delay of the dependencies among individual variables of a multivariate time series, for example, the congestion at intersection A has delayed effects on the neighboring intersection B. In addition, graph-based forecasting methods cannot capture the shared global tendency across the variables of a multivariate time series; and global-local forecasting methods cannot reflect the nonlinear inter-dependencies among variables of a multivariate time series. In this paper, we propose to combine the advantages of both approaches by integrating Adaptive Global-Local Graph Structure Learning with Gated Recurrent Units (AGLG-GRU). We learn a global graph to represent the shared information across variables. And we learn dynamic local graphs to capture the local randomness and nonlinear dependencies among variables. We apply diffusion convolution and graph convolution operations to global and dynamic local graphs to integrate the information of graphs and update gated recurrent unit for multivariate time series forecasting. The experimental results on seven representative real-world datasets demonstrate that our approach outperforms various existing methods.Item Anisotropic span embeddings and the negative impact of higher-order inference for coreference resolution: An empirical analysis(Cambridge University Press, 2024-01-25) Hou F; Wang R; Ng S-K; Zhu F; Witbrock M; Cahan SF; Chen L; Jia XCoreference resolution is the task of identifying and clustering mentions that refer to the same entity in a document. Based on state-of-the-art deep learning approaches, end-to-end coreference resolution considers all spans as candidate mentions and tackles mention detection and coreference resolution simultaneously. Recently, researchers have attempted to incorporate document-level context using higher-order inference (HOI) to improve end-to-end coreference resolution. However, HOI methods have been shown to have marginal or even negative impact on coreference resolution. In this paper, we reveal the reasons for the negative impact of HOI coreference resolution. Contextualized representations (e.g., those produced by BERT) for building span embeddings have been shown to be highly anisotropic. We show that HOI actually increases and thus worsens the anisotropy of span embeddings and makes it difficult to distinguish between related but distinct entities (e.g., pilots and flight attendants). Instead of using HOI, we propose two methods, Less-Anisotropic Internal Representations (LAIR) and Data Augmentation with Document Synthesis and Mention Swap (DSMS), to learn less-anisotropic span embeddings for coreference resolution. LAIR uses a linear aggregation of the first layer and the topmost layer of contextualized embeddings. DSMS generates more diversified examples of related but distinct entities by synthesizing documents and by mention swapping. Our experiments show that less-anisotropic span embeddings improve the performance significantly (+2.8 F1 gain on the OntoNotes benchmark) reaching new state-of-the-art performance on the GAP dataset.Item Real and synthetic Punjabi speech datasets for automatic speech recognition(Elsevier Inc, 2024-02) Singh S; Hou F; Wang RAutomatic speech recognition (ASR) has been an active area of research. Training with large annotated datasets is the key to the development of robust ASR systems. However, most available datasets are focused on high-resource languages like English, leaving a significant gap for low-resource languages. Among these languages is Punjabi, despite its large number of speakers, Punjabi lacks high-quality annotated datasets for accurate speech recognition. To address this gap, we introduce three labeled Punjabi speech datasets: Punjabi Speech (real speech dataset) and Google-synth/CMU-synth (synthesized speech datasets). The Punjabi Speech dataset consists of read speech recordings captured in various environments, including both studio and open settings. In addition, the Google-synth dataset is synthesized using Google's Punjabi text-to-speech cloud services. Furthermore, the CMU-synth dataset is created using the Clustergen model available in the Festival speech synthesis system developed by CMU. These datasets aim to facilitate the development of accurate Punjabi speech recognition systems, bridging the resource gap for this important language.Item Seasonal variation in soil and herbage CO2 efflux for a sheep-grazed alpine meadow on the north-east Qinghai-Tibetan Plateau and estimated net annual CO2 exchange(2/06/2022) Yuan H; Matthew C; He XZ; Sun Y; Liu Y; Zhang T; Gao X; Yan C; Chang S; Hou FThe Qinghai-Tibetan Plateau is a vast geographic area currently subject to climate warming. Improved knowledge of the CO2 respiration dynamics of the Plateau alpine meadows and of the impact of grazing on CO2 fluxes is highly desirable. Such information will assist land use planning. We measured soil and vegetation CO2 efflux of alpine meadows using a closed chamber technique over diurnal cycles in winter, spring and summer. The annual, combined soil and plant respiration on ungrazed plots was 28.0 t CO2 ha-1 a-1, of which 3.7 t ha-1 a-1occurred in winter, when plant respiration was undetectable. This suggests winter respiration was driven mainly by microbial oxidation of soil organic matter. The winter respiration observed in this study was sufficient to offset the growing season CO2 sink reported for similar alpine meadows in other studies. Grazing increased herbage respiration in summer, presumably through stimulation of gross photosynthesis. From limited herbage production data, we estimate the sustainable yield of these meadows for grazing purposes to be about 500 kg herbage dry matter ha-1 a-1. Addition of photosynthesis data and understanding of factors affecting soil carbon sequestration to more precisely determine the CO2 balance of these grasslands is recommended.