2022 14th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Год журнала: 2024, Номер unknown, С. 1 - 7
Опубликована: Июнь 27, 2024
Язык: Английский
2022 14th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Год журнала: 2024, Номер unknown, С. 1 - 7
Опубликована: Июнь 27, 2024
Язык: Английский
Sustainable Cities and Society, Год журнала: 2024, Номер 106, С. 105397 - 105397
Опубликована: Апрель 8, 2024
Язык: Английский
Процитировано
22Journal of Ambient Intelligence and Humanized Computing, Год журнала: 2025, Номер unknown
Опубликована: Апрель 23, 2025
Язык: Английский
Процитировано
0Applied Soft Computing, Год журнала: 2025, Номер unknown, С. 112781 - 112781
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
0Sensors, Год журнала: 2024, Номер 24(12), С. 3988 - 3988
Опубликована: Июнь 19, 2024
Managing car parking systems is a complex process because multiple constraints must be considered; these include organizational and operational constraints. In this paper, constraint optimization model for dynamic space allocation introduced. An ad hoc algorithm proposed, presented, explained to achieve the goal of our proposed model. This paper makes research contributions by providing an intelligent prioritization mechanism, considering user schedule shifts constraints, assigning suitable slots based on distribution. The implemented demonstrate applicability approach. A benchmark constructed well-defined metrics validate results achieved.
Язык: Английский
Процитировано
3Process Safety and Environmental Protection, Год журнала: 2024, Номер 205, С. 388 - 400
Опубликована: Апрель 11, 2024
Язык: Английский
Процитировано
1Опубликована: Апрель 18, 2024
Язык: Английский
Процитировано
1Mathematics, Год журнала: 2024, Номер 12(24), С. 3929 - 3929
Опубликована: Дек. 13, 2024
To address the issues of slow convergence and large errors in existing metaheuristic algorithms when optimizing neural network-based subway passenger flow prediction, we propose following improvements. First, replace random initialization method population SSA with Circle mapping to enhance its diversity quality. Second, introduce a hybrid mechanism combining dimensional small-hole imaging backward learning Cauchy mutation, which improves individual sparrow selection optimal positions helps overcome algorithm’s tendency become trapped local optima premature convergence. Finally, position update process by integrating cosine strategy an inertia weight adjustment, global search ability, effectively balancing exploitation, reducing risk insufficient precision. Based on analysis correlation between different types station flows weather factors, ISSA is used optimize hyperparameters CNN-LSTM model construct prediction based ISSA-CNN-LSTM. Simulation experiments were conducted using card swipe data from Harbin Metro Line 1. The results show that provides more accurate optimization average values standard deviations 12 benchmark test function simulations being closer values. ISSA-CNN-LSTM outperforms SSA-CNN-LSTM, PSO-ELMAN, GA-BP, CNN-LSTM, LSTM models terms error evaluation metrics such as MAE, RMSE, MAPE, improvements ranging 189.8% 374.6%, 190.9% 389.5%, 3.3% 6.7%, respectively. Moreover, exhibits smallest variation across stations. demonstrates superior parameter accuracy speed compared SSA. suitable for precise at stations, providing theoretical support density trend forecasting, organization management, emergency response, improvement service quality operational safety.
Язык: Английский
Процитировано
0Journal of Network and Computer Applications, Год журнала: 2024, Номер 230, С. 103924 - 103924
Опубликована: Июнь 20, 2024
Язык: Английский
Процитировано
02022 14th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Год журнала: 2024, Номер unknown, С. 1 - 7
Опубликована: Июнь 27, 2024
Язык: Английский
Процитировано
0