摘要
|
In recent decades, training has emerged as a crucial element in enhancing learning performance and memory retention. This research aims to elucidate the significant impact of exercise on the learning processes within the manufacturing workforce, facilitated by the potent tool of big data analytics. A pioneering hybrid methodology is introduced, which seamlessly integrates neural network techniques with the intelligent water drops optimization algorithm. To rigorously evaluate this methodology, a performance evaluation dataset comprising 1,250 samples, each characterized by a diverse array of attributes, is utilized. The integrated approach combines two pivotal techniques: feature selection empowered by the intelligent water drops algorithm and classification executed through neural networks. The findings reveal an optimal neural network configuration featuring 11 neurons in the hidden layers, along with the selection of the Pure linear (purelin) transfer function and the Train using Scaled Conjugate Gradient (traincgb) training function. The implications of this methodology are profound, demonstrating a remarkable 22% improvement over the baseline method. This underscores the pivotal role of exercise and physical activity, accounting for approximately 68%, in enhancing the learning and efficiency of the workforce. Notably, this research transcends existing studies by providing a specialized lens through which the relationship between exercise, cognitive function, and learning within the realm of workforce planning is examined. Additionally, dataset performance is bolstered through the inclusion of 875 training samples, highlighting the critical importance of homogeneous parameters in achieving superior classification outcomes. In summary, this innovative artificial neural network methodology not only exhibits unparalleled performance in comparison to existing methods but also offers invaluable insights into enhancing workforce proficiency through the transformative capabilities of big data analytics. |