Wearable Airbag System for Real-Time Bicycle Rider Accident Recognition by Orthogonal Convolutional Neural Network (O-CNN) Model

As demand for bicycles increases, bicycle-related accidents are on the rise. There are many items such as helmets and racing suits for bicycles, but many people do not wear helmets even if they are the most basic safety protection. To protect the rider from accidents, technology is needed to measure the rider’s motion condition in real time, determine whether an accident has occurred, and cope with the accident. This paper describes an artificial intelligence airbag. The artificial intelligence airbag is a system that measures real-time motion conditions of a bicycle rider using a six-axis sensor and judges accidents with artificial intelligence to prevent neck injuries. The MPU 6050 is used to understand changes in the rider’s movement in normal and accident conditions. The angle is determined by using the measured data and artificial intelligence to determine whether an accident happened or not by analyzing acceleration and angle. In this paper, similar methods of artificial intelligence (NN, PNN, CNN, PNN-CNN) to are compared to the orthogonal convolutional neural network (O-CNN) method in terms of the performance of judgment accuracy for accident situations. The artificial neural networks were applied to the airbag system and verified the reliability and judgment in advance.

Bicycle Rider Behavior and Crash Involvement in Australia

This research investigated how behaviours and attitudes of bicycle riders influence crash frequency and severity. The study recruited 1102 Australian bicycle riders for an online survey. The survey comprised questions on demographics, frequency of riding and the number and severity of traffic crashes during the last five years. The survey included the Cycling Behaviour Questionnaire and the Cyclist Risk Perception and Regulation Scale. Overall, there were low levels of errors and violations reported by participants indicating that these behaviours were on average never or rarely exhibited while riding a bicycle. Conversely, participants reported high levels of engagement in positive behaviours and reported high levels of traffic rule knowledge and risk perception. Higher rates of violations and errors were associated with increased crash likelihood, while higher rates of positive behaviours were associated with reduced rates of crash involvement in a period of 5 years. The findings highlight the relationship between errors, total crashes and crash severity Further promotion of positive behaviours amongst riders may also help to reduce the risk of crashes.

Risk of Injury and Mortality among Driver Victims Involved in Single-Vehicle Crashes in Taiwan: Comparisons between Vehicle Types

Vehicle-type specific injury severity has rarely been investigated mainly because of a lack of such information in hospital-based studies that normally exclude those who are severely injured and die on the scene. No study has been conducted either on driver characteristics in single vehicle crashes in Taiwan according to vehicle type. This was the first population-based study aiming to describe demographic characteristics in association with vehicle-specific rates of injury and fatality among driver victims involved in single-vehicle crashes in Taiwan. We presented sex and age-specific number and proportion of driver victims according to vehicle type. We calculated sex and age-specific rates of injury and fatality. Injury and fatality rates were also graphically presented. Bicycle and motorcycle rider victims generally had higher injury rates but lower fatality rates. However, older (45+) bicycle rider victims had greater fatality risk. By contrast, truck and car driver victims were generally associated with lower injury rates but with higher fatality rates. Elderly (65+ years) truck driver victims suffered from higher rates of injury and fatality. Male victims were found to have a higher fatality rate than female victims regardless of vehicle type. The vehicle-type-specific analyses of injury and fatality are considered useful in identifying single-vehicle crash victims at greater risks of injury and fatality.

Semi Automatic Bicycle using Fly Wheel Mechanism

Self-loader bike is a system for recovering the motor vita lity of the moving vehicle from the wheel put away and putting it as rotational vitality under braking in the flywheel Lot of kinetic energy is lost when a bicycle is applied brake. This loss in kinetic energy is recovered using flywheel and it stores the required energy. As per the requirement, the bicycle rider may descend or ascend the usage of energy. The flywheel increases the most intense acceleration and reduces pedal strength by 20 percent. During a drive, speeds are in the range between 15.5 and 25 km / h. The speed of the typical bike is 15.5 km/h. We are trying to increases its speed to 20km/hrby using flywheel and increase the bicycle efficiency.

Calculation of rear brake power and rear brake work during skidding on paved and gravel cycling surfaces

The use of a brake power meter at each wheel of a bicycle is a valid means to calculate energy losses due to braking. However, methodology utilizing the torque and angular velocity at each wheel independently are not able to reflect energy lost to braking when the rear wheel is skidding. This study tested the possibility of using the angular velocity of the front wheel, but the torque of the rear brake, to calculate rear brake power. Two cyclists completed 100 braking trials across three days on a mixture of paved and gravel surfaces with a mixture of skidding and non-skidding. The estimated total energy removed from the bicycle-rider system was calculated as the sum of brake work and estimates of drag and rolling resistance. This energy removed from the bicycle-rider system displayed a strong positive relationship with the change in kinetic energy of the bicycle-rider system during braking on paved (r2=0.955; p<0.0001) and gravel surfaces paved (r2=0.702; p<0.0001). There was no difference between these measurements overall (p<0.05), however there is some error of measurement when skidding on gravel. The findings in the present investigation indicate that rear brake work is underestimated when using the angular velocity at the rear wheel during skidding, but that utilising the angular velocity of the front wheel is a valid means of calculating rear brake power. Care should be taken when skidding on gravel as it is difficult to assess the linear velocity of the bicycle.

Effect of Rider Posture on Bicycle Comfort

Cyclists are exposed to vibration due to road roughness. The levels of vibration that the cyclists experience have a major effect on comfort and depend on the bicycle, rider and road characteristics. It is known that the posture of the cyclist has a relevant effect on the bicycle-cyclist system vibration response. Nevertheless, this effect has been scarcely quantified. This study focuses on the measurement of the effect of body posture on comfort while riding a bicycle. A laboratory methodology based on the measurement of the impulsive response of sensitive points of the bicycle was implemented to predict the comfort of cyclists on the road. The posture on the sagittal plane was verified during the tests. The methodology was implemented to predict the comfort of two cyclists riding a city bicycle in two postures: upright and bent forward. Experimental results showed that in the bent forward posture the acceleration levels had a significant increment for the handlebar stem and a non-significant increment for the seatpost.

Modeling and Control of an Active Stabilizing Assistant System for a Bicycle

This study designs and controls an active stabilizing assistant system (ASAS) for a bicycle. Using the gyroscopic effect of two spinning flywheels, the ASAS generates torques that assist the rider to stabilize the bicycle in various riding modes. Riding performance and the rider’s safety are improved. To simulate the system dynamic behavior, a model of a bicycle–rider system with the ASAS on the rear seat is developed. This model has 14 degrees of freedom and is derived using Lagrange equations. In order to evaluate the efficacy of the ASAS in interacting with the rider’s control actions, simulations of the bicycle–rider system with the ASAS are conducted. The results for the same rider for the bicycle with an ASAS and on a traditional bicycle are compared for various riding conditions. In three cases of simulation for different riding conditions, the bicycle with the proposed ASAS handles better, with fewer control actions being required than for a traditional bicycle.