Article
Computer Science, Information Systems
Abdelwhab Ouahab, Mohamed Faouzi Belbachir
Summary: This article introduces an adaptive fusion method based on GIHS using the Fruit Fly Optimization Algorithm in two stages to optimize band weights and modulation parameters, which outperforms other fusion methods in terms of spatial and spectral quality according to quantitative results and visual analysis.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Ting Zhu, Yuan Ren, Lifen Wang, Xuerui Zhai
Summary: The study proposes an optimal WLS weight estimation method based on the fruit fly optimization algorithm, establishing an optimal weight criterion and introducing a constrained multi-dimensional fruit fly optimization algorithm for determining the optimal WLS weight in RIMU. Simulation and experimental results show the superior performance of the proposed method compared to traditional methods for data fusion of RIMU.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Hardware & Architecture
Juanhan Cheng, Tao Shi
Summary: This paper proposes an improved fruit fly optimization algorithm to address the problem of premature convergence, which leads to poor optimization performance. By weighting the flight radius of individual fruit flies based on the number of iterations, fusing optimization trend information using the average value of the fruit fly population, and optimizing the concentration decision value calculation method, the algorithm's global and local optimization abilities are enhanced.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Energy & Fuels
Yiying Wang, Runjie Shen, Ming Ma
Summary: This study emphasizes the importance of wind power generation and the methodology of establishing a wind farm output prediction model. By considering various meteorological factors comprehensively, the accuracy of the predictions can be improved.
Article
Computer Science, Artificial Intelligence
E. Gangadevi, R. Shoba Rani, Rajesh Kumar Dhanaraj, Anand Nayyar
Summary: Crop diseases pose a threat to food security, and timely detection is challenging due to infrastructure limitations. This study focuses on accurately and timely identifying tomato plant diseases. A hybrid fruit fly optimization algorithm and support vector machine are used to reduce optimization problems, presenting a multi-objective identification method.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Energy & Fuels
Bo Gu, Huiqiang Shen, Xiaohui Lei, Hao Hu, Xinyu Liu
Summary: This paper proposes a method to improve the accuracy of photovoltaic power forecasting by using a combination of algorithms such as FCM, WOA, LSSVM, and NPKDE. By optimizing model parameters and improving calculation speed and accuracy, the forecasting accuracy was significantly improved compared to other models. The NPKDE method accurately describes the probability density distribution of forecasting error.
Article
Thermodynamics
Zhenyu Zhao, Yao Zhang, Yujia Yang, Shuguang Yuan
Summary: Load forecasting analysis is crucial for regional electric power project planning and consumption management. This paper proposes a new forecasting model that combines Grey Model and Least Squares Support Vector Machine to improve the accuracy and usability of long-term load forecasting by extracting load characteristics. Through a case study in Beijing, the results show that the electric consumption intensity exhibits positive spatial correlation and a decreasing trend overall, with increasing internal variations over time. These findings provide valuable insights for electric construction planning and the formulation of regionally energy-saving policies.
Article
Computer Science, Artificial Intelligence
Athanasios I. Salamanis, Anastasia-Dimitra Lipitakis, George A. Gravvanis, Sotiris Kotsiantis, Dimosthenis Anagnostopoulos
Summary: The study introduces an effective and efficient model for large-scale multi-step traffic forecasting, by reformulating the autoregressive model, optimizing the selection of past values, and solving the sparse least squares problem using a novel iterative method. The proposed model achieves a better balance between forecasting accuracy and computational efficiency compared to benchmark models through large scale evaluation experiments on real-world traffic datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Construction & Building Technology
Kai Zhang, Ke Zhang, Rui Bao, Xianghua Liu
Summary: The carbonation of concrete structures is a serious problem due to increasing global CO2 levels, and this study proposes a hybrid prediction framework using LSSVM and metaheuristic algorithms to accurately predict carbonation depth in concrete with fly ash. A database of 500 samples is created for model building, and the hybrid models show superior accuracy compared to empirical models.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Engineering, Mechanical
Ayad G. Baziyad, Adnan S. Nouh, Irfan Ahmad, Abdulaziz Alkuhayli
Summary: This paper proposes a kernel-based learning method to enhance the learning and generalization capabilities of models for describing and compensating the hysteresis phenomenon in piezoelectric actuators. Two control schemes are evaluated through real-time experiments, showing improved tracking performance.
Article
Computer Science, Information Systems
Xiao He, Ye Li, Jian Tan, Bin Wu, Feifei Li
Summary: Seasonal-trend decomposition is a fundamental concept in time series analysis, but existing methods are not efficient for real-time analysis. In this paper, we propose OneShotSTL, an algorithm that can decompose time series online with high efficiency and accuracy. OneShotSTL is more than 1,000 times faster than batch methods and achieves comparable or even better accuracy. Experimental results on benchmark datasets demonstrate its superiority.
PROCEEDINGS OF THE VLDB ENDOWMENT
(2023)
Article
Computer Science, Artificial Intelligence
Yi Fan, Pengjun Wang, Majdi Mafarja, Mingjing Wang, Xuehua Zhao, Huiling Chen
Summary: The fruit fly optimization algorithm (FOA) is a swarm-based algorithm inspired by fruit flies' food search behaviors in nature. The conventional FOA, while simple and concise, has limitations in exploration and exploitation abilities when used for different optimization problems. By introducing an improved FOA approach called BSSFOA, which utilizes bat sonar strategy for global optimization and a hybrid distribution mechanism for local optimization, better solutions can be found in both continuous and discrete optimization problems.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Engineering, Geological
Wenping Gong, Shan Tian, Lei Wang, Zhibin Li, Huiming Tang, Tianzheng Li, Liang Zhang
Summary: This paper presents a new method for interval prediction of landslide displacement, integrating dual-output least squares support vector machine and particle swarm optimization algorithms. Case studies demonstrate that the proposed method has the best overall performance compared with other existing methods and provides accurate and reliable results.
Article
Multidisciplinary Sciences
Md. Nahid Pervez, Wan Sieng Yeo, Mst. Monira Rahman Mishu, Md. Eman Talukder, Hridoy Roy, Md. Shahinoor Islam, Yaping Zhao, Yingjie Cai, George K. Stylios, Vincenzo Naddeo
Summary: Despite limited simulation studies, this research developed a sustainable and effective electrospinning process by combining the design of experiments with machine learning prediction models. The locally weighted kernel partial least squares regression (LW-KPLSR) model, based on response surface methodology, outperformed other models in predicting the membrane diameter.
SCIENTIFIC REPORTS
(2023)
Article
Environmental Sciences
Feng Jiang, Wenya Zhang, Zijun Peng
Summary: This paper proposes a multivariate adaptive step fruit fly optimization algorithm (MAFOA) for short-term power load forecasting. It optimizes the smoothing parameter of the generalized regression neural network (GRNN) and incorporates external factors to improve accuracy. Empirical analysis demonstrates that MAFOA-GRNN outperforms benchmark methods.
FRONTIERS IN ENVIRONMENTAL SCIENCE
(2022)