Leveraging Artificial Intelligence for Predicting Music Popularity Using Social Media

El Profesional de la Informacion, Год журнала: 2025, Номер 33(5)

Опубликована: Янв. 7, 2025

Music industry has been remarkably influenced by artificial intelligence (AI) due to the ability of latter predict song popularity based on social networking sites data, though it is rather difficult success a in any given scenario. This study premise that improved accuracy prediction can be achieved developing adaptive algorithms sensitive changing trends data. Therefore, this proposes new approach called Dynamic Honey Badger Optimization-Driven Intelligent Long Short-Term Memory (DHB-ILSTM), model enhance music forecasting with media metrics, incorporating audio features. Features were extracted from sources like Spotify and genre-wise newly released tracks. During pre-processing, Min-Max normalization technique was utilized, inputs standardized, while missing values filled in. Feature extraction dimensionality reduction used LDA. It found DHB-ILSTM algorithm Python superior, regarding without data comparison, because yielded an 93% for features, recall 90%, F1-score 91% precision value 88%. The findings underscore versatility integrating heterogeneous adapting dynamic trends, meaning strong solution using AI advance optimization techniques.

Язык: Английский

Three-Dimensional Unmanned Aerial Vehicle Path Planning in Simulated Rugged Mountainous Terrain Using Improved Enhanced Snake Optimizer (IESO)

World Electric Vehicle Journal, Год журнала: 2025, Номер 16(6), С. 295 - 295

Опубликована: Май 27, 2025

The challenging terrain and deep ravines that characterize mountainous regions often result in slower path planning suboptimal flight paths for unmanned aerial vehicles (UAVs) when traditional meta-heuristic optimization algorithms are employed. This study proposes a novel Improved Enhanced Snake Optimizer (IESO) three-dimensional tested it simulated rugged with obstacles restricted “no-fly zone”. initialization process the enhanced snake optimizer is refined by integrating Chebyshev chaotic map. Additionally, non-monotonic factor introduced to modulate “temperature”. temperature controls freedom of movement within solution space. Furthermore, boundary condition incorporated into dynamic opposition learning mechanism. These modifications collectively reduce likelihood population convergence local optima during optimization. feasibility IESO validated through time complexity global analyses. Comparative simulation experiments benchmarked against five state-of-the-art biologically inspired across test functions path-planning scenarios. Experimental results show compared commonly used algorithms, algorithm improves quality trajectory nearly 30% on average. Particularly original SO algorithm, demonstrates performance enhancement exceeding 36%, proving its superiority UAV over complex terrain.

Язык: Английский

Enhanced Multi-Objective Evolutionary Mating Algorithm with Improved Crowding Distance and Levy Flight for Optimizing Comfort Index and Energy Consumption in Smart Buildings

Franklin Open, Год журнала: 2025, Номер unknown, С. 100286 - 100286

Опубликована: Июнь 1, 2025

Язык: Английский