The study develops an approach adopted by artificial neural networks (ANN) to model the relationship between pondscape and waterbird diversity. Study areas with thousands of irrigation ponds are unique geographic feat...
详细信息
In personalized federated learning (PFL), it is widely recognized that achieving both high model generalization and effective personalization poses a significant challenge due to their conflicting nature. As a result,...
详细信息
Preference-inspired co-evolutionary algorithms (PICEAs) are a novel class of population-based approaches for multi-objective optimization. PICEA-g is one realization of PICEAs in which goal vectors are taken as prefer...
详细信息
ISBN:
(纸本)9781479904532
Preference-inspired co-evolutionary algorithms (PICEAs) are a novel class of population-based approaches for multi-objective optimization. PICEA-g is one realization of PICEAs in which goal vectors are taken as preferences and are co-evolved with the candidate solutions during the search. The performance of PICEA-g is affected by the distribution of the co-evolved goal vectors. In PICEA-g, new goal vectors are generated within pre-defined bounds determined by the ideal and anti-ideal points in each generation. Such bounds are often unknown or at least problem knowledge requires. In this paper, firstly, we analyse the influence of different initial bounds to the performance of PICEA-g. Then, we propose a method, called cutting plane, which adaptively sets proper bounds for the generation of goal vectors, adjusting the search effort toward different objective appropriately, and therefore guide the candidate solutions toward the Pareto optimal front efficiently. Experimental results show that this adaptive approach is effective.
The total systems approach focuses on human performance and ensures capabilities, limitations and risks are identified and managed throughout the system development lifecycle. HSI is the process to ensure that systems...
The total systems approach focuses on human performance and ensures capabilities, limitations and risks are identified and managed throughout the system development lifecycle. HSI is the process to ensure that systems are designed and maintained such that they enhance human performance and capabilities while considering humans limitations to avoid high risk designs. The HSI process utilizes and integrates the interdependent multi-disciplinary aspects of various domains together within the systemsengineering perspective. Since HSI processes have a top priority in systems design; this paper will introduce a new approach for modeling human capabilities and limitations in systems design. Human considerations in systems development will be modeled using systems Modeling Language (SysML), a general-purpose visual modeling language for designing, specifying, analyzing, and verifying complex systems (Friedenthal et al., 2008).
Speaker verification systems usually suffer from the mismatch problem between training and evaluation data, such as speaker population mismatch, the channel and environment variations. In order to address this issue, ...
详细信息
The multi-armed bandit (MAB) is a classical online optimization model for the trade-off between exploration and exploitation. The traditional MAB is concerned with finding the arm that minimizes the mean cost. However...
详细信息
In order to control the temperature distribution on the wafer in a rapid thermal processing system, we develop a learning control approach based on the dominant modes of the system state. Firstly, the dominant modes o...
详细信息
In order to control the temperature distribution on the wafer in a rapid thermal processing system, we develop a learning control approach based on the dominant modes of the system state. Firstly, the dominant modes of the system state are extracted through the K-L method. Galerkin's method is utilized to construct the reduced model of the system from the dominant modes. Then learning control approach is designed based on this reduced model. Simulations are performed by heating the wafer from 300K to 1000K with the proposed control method. Simulation results show that the proposed control method has superb ability to reduce the temperature tracking error and improve the temperature uniformity among the wafer.
Faculty evaluation is a crucial component of human resource management in higher education institutions. One of the main issues of evaluation is how to assess overall performance of faculty members based on multiple c...
详细信息
Faculty evaluation is a crucial component of human resource management in higher education institutions. One of the main issues of evaluation is how to assess overall performance of faculty members based on multiple criteria. In this paper, we propose a faculty evaluation index system by employing group Multiple Criteria Decision Making (MCDM) based on fuzzy Analytic Hierarchy Process (AHP). Specifically, after determining the criteria and attributes, the evaluation hierarchy is established. The weights of criteria and attributes are then calculated by the fuzzy AHP method. Employing the fuzzy AHP in group decision making facilitates a consensus of decision-makers and reduces uncertainty in decision making. The evaluation process can then be conducted by the use of the multiple criteria measurement method. A case application is also used to illustrate the proposed framework. The application of this framework can make the evaluation more scientific, accurate, and objective. It is expected that this work may serve as an assistance tool for managers of higher education institutions in improving the educational quality level.
Reinforcement learning (RL) is a simulation-based technique to solve Markov decision problems or processes (MDPs). It is especially useful if the transition probabilities in the MDP are hard to find or if the number o...
详细信息
ISBN:
(纸本)9781424457717
Reinforcement learning (RL) is a simulation-based technique to solve Markov decision problems or processes (MDPs). It is especially useful if the transition probabilities in the MDP are hard to find or if the number of states in the problem is too large. In this paper, we present a new model-based RL algorithm that builds the transition probability model without the generation of the transition probabilities; the literature on model-based RL attempts to compute the transition probabilities. We also present a variance-penalized Bellman equation and an RL algorithm that uses it to solve a variance-penalized MDP. We conclude with some numerical experiments with these algorithms.
Almost all the published studies on container handle positions have used the psychophysical, physiological, and biomechanical criteria to evaluate the best handle locations on container. The primary intent of this inv...
Almost all the published studies on container handle positions have used the psychophysical, physiological, and biomechanical criteria to evaluate the best handle locations on container. The primary intent of this investigation was to determine if force endurance relationship curves could be used as criterion for comparing the handle positions. Ten subjects participated in a factorial experiment involving four handle positions (2/2, 3/7, 8/8, and 6/8), and four levels of exertion (25%, 50%, 75%, and 100% of maximum lifting capacity). On any treatment condition, the subjects held the box till their endurance limit. The endurance time and the rate of perceived exertion (RPE) were the dependent measures. For the RPE, it was observed that the asymmetric position 6/8 was the best. Similarly the handle position 6/8 had the longest endurance as observed by a third order polynomial fit. The differences among the handle position were consistent across all levels and exertions tested. Further, it appears that the maximum lifting capacity is closer to the grip strength of the non-dominant hand.
暂无评论