Abidi Mustufa Haider, Alkhalefah Hisham, Almutairi Zeyad
Advanced Manufacturing Institute, King Saud University, P.O. Box 800, 11421, Riyadh, Saudi Arabia.
Department of Mechanical Engineering, College of Engineering, King Saud University, P.O. Box 800, 11421, Riyadh, Saudi Arabia.
Sci Rep. 2025 Feb 25;15(1):6756. doi: 10.1038/s41598-025-90360-1.
In healthcare applications, automatic and intelligent movement recognition systems in Ambient Assisted Living (AAL) are designed for elderly and disabled persons. The AAL provides assistance as well as secure feelings to disabled persons and elderly individuals. In AAL, the movement recognition process has been emerging in recent days. The automatic and safe living of the disabled person is ensured by performing movement recognition in AAL. Movement recognition in the AAL is developed for disabled and elderly people and is also performed to provide healthcare assistance to the elderly and disabled person. The weighted deep learning model and a hybrid heuristic algorithm are proposed to achieve this goal. The required input data is initially gathered from the standard data sources. Subsequently, the essential deep features are extracted from the input data using a Convolutional Autoencoder. Finally, the resultant features are subjected to the movement recognition model, termed as Weighted Residual Recurrent Neural Network. For achieving a better training and testing process, the weights in the RRNN model are optimally selected by using the hybrid algorithm named Hybrid Rat Swarm with Coati Optimization Algorithm, which is developed with the integration of the Rat Warm Optimization and Coati Optimization. The movement recognition results are used for providing medical assistance to elderly and disabled persons. Lastly, the efficacy of the suggested strategy is validated with different measures. From the experiments, the proposed system attains standard results in terms of improved system performance and accuracy that can aid in significantly recognizing human movements.
在医疗保健应用中，环境辅助生活（AAL）中的自动智能运动识别系统是为老年人和残疾人设计的。AAL为残疾人和老年人提供帮助以及安全感。近年来，AAL中的运动识别过程不断涌现。通过在AAL中进行运动识别，确保了残疾人的自动安全生活。AAL中的运动识别是为残疾人和老年人开发的，也是为了向老年人和残疾人提供医疗保健帮助而进行的。为实现这一目标，提出了加权深度学习模型和混合启发式算法。所需的输入数据最初从标准数据源收集。随后，使用卷积自动编码器从输入数据中提取基本深度特征。最后，将所得特征输入到称为加权残差循环神经网络的运动识别模型中。为了实现更好的训练和测试过程，使用名为混合大鼠群与长鼻浣熊优化算法的混合算法对RRNN模型中的权重进行优化选择，该算法是将大鼠群优化和长鼻浣熊优化集成开发的。运动识别结果用于为老年人和残疾人提供医疗帮助。最后，用不同的指标验证了所提策略的有效性。从实验结果来看，所提出的系统在提高系统性能和准确性方面取得了标准结果，这有助于显著识别人类运动。
