High-level athletes participate in various events that need extreme fitness and stamina. Usually, after competitions, the athletes take part in systematic physical fitness and specialized skills training. The daily training sessions of an athlete are often of higher intensity level. This kind of long-term and high-intensity training affects an athlete both physically and mentally and overloads him/her, leading to sports injuries. As a result, an athlete is no longer capable to perform high-intensity training due to these injuries and unable to achieve the desired results in the competition. Therefore, the need for an intelligent system arises to evaluate, predict and detect sports injuries effectively. The significance of neural networks for target recognition motivates us to propose a novel dual-feature fusion neural network model for athlete injury estimation. Our proposed model solves the problem of feature loss by using a 1 × 1 convolution and hyperlink to form a dual-fusion structure to enhance effective discrimination. Multiple experiments have been performed using different classification models. The performance of the utilized models, including the proposed model, has been evaluated with the help of numerous performance evaluation metrics. Various preprocessing techniques have been used in this study. The proposed model attained an excellent classification accuracy of 97.0%, a sensitivity of 95.70%, and a specificity of 97.54%. Experimental results show that the performance of the proposed model is much better than the rest of the classification models used in this study.

高水平运动员参加各种需要极端体能和耐力的赛事。运动员通常在比赛结束后参加系统的体能训练和专业技能训练。运动员的日常训练通常强度更高。这种长期、高强度的训练，对运动员的身心都造成影响，使他/她超负荷工作，导致运动损伤。结果，运动员因这些伤病不再能够进行高强度训练，无法在比赛中取得理想的成绩。因此，需要一个智能系统来有效地评估、预测和检测运动损伤。神经网络对目标识别的重要性促使我们提出一种新的双特征融合神经网络模型用于运动员损伤估计。我们提出的模型通过使用 1×1 卷积和超链接形成双重融合结构来增强有效区分，从而解决了特征丢失问题。已经使用不同的分类模型进行了多次实验。已在众多性能评估指标的帮助下评估了所使用模型（包括所提出的模型）的性能。本研究中使用了各种预处理技术。所提出的模型达到了97.0%的优秀分类准确率、95.70%的灵敏度和97.54%的特异性。