Recommender systems have become essential in modern information systems and Internet applications by delivering personalized and pertinent content to users. While conventional recommendation algorithms usually priorit...
详细信息
Recommender systems have become essential in modern information systems and Internet applications by delivering personalized and pertinent content to users. While conventional recommendation algorithms usually prioritize optimizing a single objective, it is now evident that considering additional metrics is crucial for improving the overall user experience. Despite the importance of considering multiple objectives, conventional recommendation models face the challenge of balancing these objectives, which can sometimes conflict with each other. To tackle this challenge, there is a growing interest in multi-objective recommender systems (MORS) that consider multiple objectives simultaneously and provide a more personalized and varied set of recommendations. MORS can optimize recommendations based on various metrics, including accuracy, diversity, novelty, and user satisfaction, leading to more efficient and personalized recommendation systems. The objective of this paper is to conduct a systematic review study to assess the current state of research in the field of MORS and identify potential avenues for future exploration. The study selection procedure includes 78 primary studies published from 2019 to January 2023. These preliminary studies are categorized based on different variables to address the research questions outlined in this study. The findings of this systematic review study reveal a diverse range of applications, objectives, datasets, methodologies, and evaluation metrics utilized in the field of MORS. Additionally, this review offers a crucial overview of the current state of research in this area, highlighting the existing challenges and future directions for enhancing the efficiency of MORS. These outcomes can benefit both professionals and academic researchers in the development and implementation of effective MORS. & COPY;2023 Elsevier Ltd. All rights reserved.
This paper introduces new techniques for efficient use of electromagnetic transient simulators combined with optimization algorithms to optimize power systems with converter-tied renewable resources. This work is moti...
详细信息
This paper introduces new techniques for efficient use of electromagnetic transient simulators combined with optimization algorithms to optimize power systems with converter-tied renewable resources. This work is motivated by several challenges that must be overcome for simulation-based optimal design, including high computational burden of simulating large switching systems, repetitive nature of the design cycle, and large number of variables that need to be handled. Two screening methods are proposed in this paper to identify the parameters that do not influence the optimal solution significantly and hence can be ignored. Moreover, hybridization of optimization algorithms and parallel processing techniques are explored to achieve additional computational benefits. Case studies of systems with different complexity and number of variables are used to demonstrate the effectiveness of the proposed techniques.
To address the challenges posed by highly time-sensitive targets with uncertainty and unpredictability in multi-satellite cooperative observation, conventional intelligent optimization algorithms often suffer from tim...
详细信息
Online Feedback optimization uses optimization algorithms as dynamic systems to design optimal control inputs. The results obtained from Online Feedback optimization depend on the setup of the chosen optimization algo...
详细信息
The growing interest in nuclear power has brought attention back to the general condition of nuclear power plants. In fact, according to the main intergovernmental organisations responsible for nuclear energy, more th...
详细信息
The growing interest in nuclear power has brought attention back to the general condition of nuclear power plants. In fact, according to the main intergovernmental organisations responsible for nuclear energy, more than 150 basic nuclear facilities (in-service reactors, downgraded reactors, fuel fabrication plants, reprocessing plants, and waste storage areas) should be seriously checked for safety reasons, while many others are close to the end of their lifecycles (lasting generally around 50-60 years) - thus, there is an urgent need for research into the management of Nuclear Decommissioning Projects (NDPs). In particular, the high complexity of these projects makes it fundamental to implement strong risk management procedures, aimed at identifying and analyzing all possible hazards, and finding and implementing the appropriate risk response actions. This paper focuses on the selection of mitigation actions and proposes optimizationisation algorithms to select the most time-effective set of risk responses for a nuclear decommissioning project. A single case study of an Italian completed NDP was employed to investigate the application of optimization techniques in the mitigation action selection phase, considering also secondary risks and secondary mitigation action. The results show that the performance that would have been achieved through the optimization algorithm would have been superior, both from the point of view of a reduced time delay, and in terms of a more effective balance between overall risk coverage and implementation costs.
Microsystems are widely used in 5G, the Internet of Things, smart electronic devices and other fields, and signal integrity (SI) determines their performance. Establishing accurate and fast predictive models and intel...
详细信息
Microsystems are widely used in 5G, the Internet of Things, smart electronic devices and other fields, and signal integrity (SI) determines their performance. Establishing accurate and fast predictive models and intelligent optimization models for SI in microsystems is extremely essential. Recently, neural networks (NNs) and heuristic optimization algorithms have been widely used to predict the SI performance of microsystems. This paper systematically summarizes the neural network methods applied in the prediction of microsystem SI performance, including artificial neural network (ANN), deep neural network (DNN), recurrent neural network (RNN), convolutional neural network (CNN), etc., as well as intelligent algorithms applied in the optimization of microsystem SI, including genetic algorithm (GA), differential evolution (DE), deep partition tree Bayesian optimization (DPTBO), two stage Bayesian optimization (TSBO), etc., and compares and discusses the characteristics and application fields of the current applied methods. The future development prospects are also predicted. Finally, the article is summarized.
Introduction: Photovoltaic systems offer immense potential as a future energy source, yet maximizing their efficiency presents challenges, notably in achieving optimal voltage due to their nonlinear behavior. Operatin...
详细信息
Optimizing hydraulic machinery is a critical research area within the field of fluid mechanics, aiming to enhance product design efficiency and improve performance while reducing development time. The application of i...
详细信息
Optimizing hydraulic machinery is a critical research area within the field of fluid mechanics, aiming to enhance product design efficiency and improve performance while reducing development time. The application of intelligent algorithms and combinatorial optimization strategies has become increasingly prevalent in this domain, providing a comprehensive understanding of optimization-related theoretical developments. Recently, the emergence of ISIGHT software as a new technology for software integration platforms has opened new avenues for optimization in hydraulic machinery. By leveraging intelligent algorithms and combinatorial optimization strategies, ISIGHT software provides a comprehensive framework for optimizing hydraulic machinery. This paper serves as an introduction to ISIGHT software, highlighting its advantages in addressing optimization problems. It presents a detailed examination of the process and technology involved in hydraulic machinery optimization based on ISIGHT software, along with its practical application. Furthermore, the paper summarizes the future development trends of ISIGHT software, offering engineers a theoretical foundation and reference for optimizing hydraulic machinery performance. Overall, this paper provides a valuable contribution to the field of hydraulic machinery optimization, showcasing the potential of ISIGHT software.
Due to the scarcity of earthquake records and the necessity of the earthquakes matched with the predefined design response spectrum (DRS) for time history analysis, designers need to generate artificial earthquakes. T...
详细信息
Due to the scarcity of earthquake records and the necessity of the earthquakes matched with the predefined design response spectrum (DRS) for time history analysis, designers need to generate artificial earthquakes. The smoothness of the DRS prevents conformity in the majority of methods, and deviation happens, especially in the constant region. To overcome this condition, the present study intends to incorporate the optimization algorithm with the synthetic earthquake method to reach the ASCE DRS. Indeed, the statistical algorithm is utilized to explore the global optimum with more accuracy and faster convergence in comparison with other algorithms. The results demonstrate that the proposed method is ideally compatible with the DRS with trivial errors. Furthermore, the novel approach has been applied to Kobe and Tabas earthquakes in order to extract the envelope function to improve compatibility in the time domain. In essence, the proposed method is not only compatible with the DRS simply but also appropriate for simulating real earthquakes. Eventually, with regard to the recommendation of seismic regulations for applying several records in dynamic analysis, one of the robust advantages of this method is to generate various earthquakes compatible with the specific target spectrum.
In this paper, we proposed a meerkat optimization algorithm(MOA) by simulating the behavior pattern of meerkats in nature. MOA is mainly inspired by the survival strategies of meerkat populations, whose sentinel mecha...
详细信息
In this paper, we proposed a meerkat optimization algorithm(MOA) by simulating the behavior pattern of meerkats in nature. MOA is mainly inspired by the survival strategies of meerkat populations, whose sentinel mechanism controls meerkats to switch between different behavior patterns. Some mathematical properties of meerkat optimization algorithm are proved, and the advantages of MOA are verified with classical optimization test functions. MOA is applied to solve real-world engineering problems with constraints, which proves the effectiveness and superiority of MOA in solving such problems.
暂无评论