The randomness of passengers’ travel and the blindness of empty drivers seeking passengers can lead to a serious imbalance in the spatio-temporal distribution of taxi supply and demand. In order to realize the accurate prediction of taxi demand, promote a balance between taxi supply and demand, and respond to the requirements of the sustainable development of urban transportation, a travel demand prediction model based on Sparrow Search Algorithm incorporating sine-cosine and Cauchy variants (SCSSA), Convolutional Neural Network (CNN), and Bi-directional Long Short-Term Memory (BiLSTM) is proposed. The key factors affecting travel demand are identified by constructing a set of influencing factors for feature correlation analysis. In order to overcome the overfitting or underfitting phenomenon caused by the improper parameter configuration of the CNN-BiLSTM model, the SCSSA algorithm is utilized to optimize the model. By fine tuning the model parameters, the algorithm enhanced the model’s adaptability to dataset characteristics and improved the accuracy of the prediction results. Compared with CNN, LSTM, CNN- LSTM, CNN-BiLSTM, and SSA-CNN-BiLSTM models, the Root Mean Square Error is decreased by 10.77 on average.

Distracted driving is one of the primary causes of road traffic accidents. Behavior recognition technology based on machine vision has emerged as a research hotspot due to its non-contact and high-efficiency nature. To address the challenges of complex lighting conditions in the driver’s cabin, low detection accuracy for small-scale keypoints, and the difficulty in effectively characterizing behavioral features, this paper proposes a distracted driving behavior recognition method based on an improved YOLOv8n-Pose model and multi-feature fusion. First, the original YOLOv8n-Pose model is optimized. A P2 detection layer is added to enhance the feature extraction capabilities for small-scale human keypoints, and the SE attention module is incorporated to improve the model’s robustness under complex lighting conditions. In addition, the loss function is replaced with focal loss to tackle the class imbalance problem, thus forming the YOLOv8n-PSF-Pose keypoint detection network. Subsequently, based on the coordinates of 12 human keypoints extracted by this network, a multi-dimensional feature vector is constructed, which takes joint angles as the core and integrates the relative distances between keypoints and the number of valid keypoints. Finally, a BP neural network is adopted to classify the constructed feature vectors, enabling the accurate recognition of six typical distracted driving behaviors (normal driving, drinking or eating, making phone calls, using mobile phones, operating vehicle infotainment systems, and turning around to fetch items). The experimental results show that the improved YOLOv8n-PSF-Pose model achieves an mAP50 of 93.8% in keypoint detection, which is 6.7 percentage points higher than the original model; the BP classification model based on multi-feature fusion achieves an F1-score of 97.7% in the behavior recognition task, which is significantly better than traditional classifiers such as SVM and random forest, and the image processing speed on the NVIDIA RTX 3090TI reaches a high throughput of 45 FPS. This proves that the proposed method achieves an excellent balance between accuracy and speed. This study provides an effective solution for the real-time and accurate recognition of distracted driving behaviors.