A Novel Intelligent Approach to Lane-Change Behavior Prediction for Intelligent and Connected Vehicles.

The prediction of lane-change behavior is a challenging issue in intelligent and connected vehicles (ICVs), which can help vehicles predict in advance and change lanes safely. In this paper, a novel intelligent approach, which considering both the driving style-based lane-change environment and the driving trajectory-related parameters of the ICV and surrounding vehicles, is proposed to predict the lane-change behaviors for ICVs. By analyzing the characteristics of the lane-change behavior of the vehicle, a modified dataset for the prediction of lane-change behavior was established based on the Next-Generation Simulation (NGSIM) dataset, which is made up of real vehicle trajectories collected by camera. In the proposed approach, the hidden Markov model (HMM)-based model is designed to judge whether the current environment is suitable for lane change according to the driving environment parameters around the vehicle; then according to the driving state of the vehicle, a learning-based prediction-then-judgment model is proposed and designed to realize the prediction of the ICV's lane-change behavior. Experiments are implemented by using the modified dataset. From the experimental results, the lane-change probability value on the target lane in the truth of the lane-change behavior calculated by the designed HMM-based model is basically above 0.5, indicating that the model can make a more accurate judgment on the surrounding lane-change environment. The proposed learning-based prediction-then-judgment model has an accuracy of 99.32% for the prediction of lane-change behavior, and the accuracy of the lane-change detection algorithm in the model is 99.56%. The experimental results show that the proposed approach has a good performance in the prediction of lane-change behavior, which could effectively assist ICVs to change lanes safely.

Effect of Tirofiban on new cerebral microbleeds after mechanical thrombectomy in patients with acute ischemic stroke.

OBJECTIVE: The aim of this study was to analyze the effect of tirofiban on new cerebral microhemorrhage after mechanical thrombectomy in patients with acute ischemic stroke. METHODS: In total, 203 patients with acute ischemic stroke treated by mechanical thrombectomy in our department of neurology were enrolled as the research objects. The patients were divided into two groups: the patients who used tirofiban within 24 h after surgery were assigned to the study group (78 subjects), while patients who did not use tirofiban were assigned to the conventional group (125 subjects). Magnetic resonance imaging was used to detect new-onset cerebral microbleeds in patients with stroke after surgery. The National Institute of Health Stroke Scale, modified ranking scale, and activity of daily living scale were used to assess the prognosis of patients, and the general data and the occurrence of adverse effects between two groups were compared to comprehensively evaluate the efficacy and safety of tirofiban. RESULTS: The proportion of atrial fibrillation in the research group was significantly lower than that in the conventional group. The research group had a much lower rate of new-onset cerebral microbleeds than the conventional group (p<0.001). There was no significant difference in the proportion of adverse reactions between the two groups (p>0.05). CONCLUSION: The application of tirofiban in mechanical thrombectomy of patients with acute ischemic stroke has high safety, effectively reduces the occurrence of new cerebral microhemorrhage, and provides a guarantee for patient safety.

Effect of different operation time on surgical effect and quality of life in patients with severe hypertensive intracerebral hemorrhage.

OBJECTIVE: To investigate the effect of different operation time on the surgery effect and quality of life of patients with severe hypertensive cerebral hemorrhage. METHODS: A total of 98 patients with severe hypertensive cerebral hemorrhage were selected in this prospective study. According to the random number table, 98 patients were divided into group A and group B. About 47 patients in group A received surgical treatment within 6 hours after onset of a cerebral hemorrhage and 51 patients in group B received surgical treatment within 6-24 hours after onset of a cerebral hemorrhage. The effect of the operation, quality of life (the World Health Organization Quality of Life Scale Brief Version, WHOQOL-BREF) score, neuro function (National Institute of Health stroke scale, NIHSS), the ability of daily living (Barthel index), athletic ability (Fugl-Meyer motor function score), complications and prognosis (GOS) were compared between the two groups. RESULTS: The total effective rate of operation in group A (91.49%) was higher than that in group B (76.47%), and the incidence of complications (8.70%) was lower than that in group B (27.08%; all P<0.05). NIHSS score of group A was lower than that of group B, and the WHOQOL-BREF score was higher than that of group B three months after the operation (all P<0.05). Barthel Index and Fugl-Meyer motor function scores of group A were higher than those of group B three months after the operation (all P<0.05). The prognosis of group A was better than group B three months after the operation (P<0.05). CONCLUSION: Operation performed within 6 hours after the onset of cerebral hemorrhage is useful in the treatment of severe hypertensive intracerebral hemorrhage. It can effectively improve patients' neurological function, the ability of daily living and motor function without increasing complications and, the quality of life, as well as the prognosis of patients.

Joint Optimization of Multi-Hop Broadcast Protocol and MAC Protocol in Vehicular Ad Hoc Networks.

Beacon messages and emergency messages in vehicular ad hoc networks (VANETs) require a lower delay and higher reliability. The optimal MAC protocol can effectively reduce data collision in VANETs communication, thus minimizing delay and improving reliability. In this paper, we propose a Q-learning MAC protocol based on detecting the number of two-hop neighbors. The number of two-hop neighbors in highway scenarios is calculated with very little overhead using the beacon messages and neighbor locations to reduce the impact of hidden nodes. Vehicle nodes are regarded as agents, using Q-learning and beacon messages to train the near-optimal contention window value of the MAC layer under different vehicle densities to reduce the collision probability of beacon messages. Furthermore, based on the contention window value after training, a multi-hop broadcast protocol combined with contention window adjustment for emergency messages in highway scenarios is proposed to reduce forwarding delay and improve forwarding reliability. We use the trained contention window value and the state information of neighboring vehicles to assign an appropriate forwarding waiting time to the forwarding node. Simulation experiments are conducted to evaluate the proposed MAC protocol and multi-hop broadcast protocol and compare them with other related protocols. The results show that our proposed protocols outperform the other related protocols on several different evaluation metrics.

Learning-Based Lane-Change Behaviour Detection for Intelligent and Connected Vehicles.

Detection of lane-change behaviour is critical to driving safety, especially on highways. In this paper, we proposed a method and designed a learning-based detection model of lane-change behaviour in highway environment, which only needs the vehicle to be equipped with velocity and direction sensors or each section of the highway to have a video camera. First, based on the Next Generation Simulation (NGSIM) Interstate 80 Freeway Dataset, we analyzed the relevant features of lane-changing behaviour and preprocessed the data and then used machine learning algorithms to select the suitable features for lane-change detection. According to the result of feature selection, we chose the lateral velocity of the vehicle as the lane-change feature and used machine learning algorithms to learn the lane-change behaviour of the vehicle to detect it. From the dataset, continuous data of 14 vehicles with frequent lane changes were selected for experimental analysis. The experimental results show that the designed KNN lane-change detection model has the best performance with detection accuracy between 89.57% and 100% on the selected dataset, which can well complete the vehicle lane-change detection task.