Vehicle Trajectory Prediction using GAN

This paper presents a novel probabilistic data-driven approach to trip-level energy consumption estimation of battery electric vehicles (BEVs). As there are very few electric vehicle (EV) charging stations, EV trip energy consumption estimation can make EV routing and charging planning easier for drivers. In this research article, we propose a new driver behavior-centric EV energy consumption estimation model using probabilistic neural networks with model uncertainty. By incorporating model uncertainty into neural networks, we have created an ensemble of neural networks using Monte Carlo approximation. Our method comprehensively considers various vehicle dynamics, driver behavior, and environmental factors to estimate EV energy consumption for a given trip. We propose relative positive acceleration (RPA), average acceleration, and average deceleration as driver behavior factors in EV energy consumption estimation, and this paper shows that the use of these driver behavior features improves the accuracy of the EV energy consumption model significantly. Instead of predicting a single-point estimate for EV trip energy consumption, this proposed method predicts a probability distribution for the EV trip energy consumption. The experimental results of our approach show that our proposed probabilistic neural network with weight uncertainty achieves a mean absolute percentage error of 9.3% and outperforms other existing EV energy consumption models in terms of accuracy.

The purpose of this study was to identify the effects of Taekwondo training on leadership and the relationship between the leadership of girl’s middle school students and community spirit and to provide basic materials for various educational program development to nurture leadership that can be used in Taekwondo Gym. In this study, preliminary survey was made on the parents of Taekwondo Gym. This study was performed according to the following study procedures. First, on 250 girl’s middle school students of the students who have been trained in Taekwondo Gym. in Daegu for more than six months were selected through Convenience Sampling and were asked to answer the survey in self-administration method. Among the 250 returned answers, 238 answers ex-cluding insincere or incomplete ones were analyzed as valid samples. Second, statistical verification was made according to the purpose of material analysis using SPSS Program 23.0. General characteristics were identified by frequency analysis and for the reliability verification cronbach s α coefficient was calculated. Taekwondo train-ing factors, leadership skill factors and community spirit factors were analyzed for the factor analysis, while the effects of Taekwondo training factors on the leadership and community spirit factors were analyzed by multi regression analysis. The following conclusions were made according to the above research methods and material analysis methods. First, in the effects of Taekwondo training on leadership skill, emotional factors, living attitude factors influenced decision making factors, and emotional factors, social factors, physical factors and living atti-tude factors influenced self-understanding factors. Second, in the effects of Taekwondo training on community spirit, social factors and living attitude factors of Taekwondo training influenced altruism factors and emotional factors and social factors influenced social responsibility factors. Third, in the effects of leadership skill on com-munity spirit, self-understanding factors and leadership factors influenced altruism and self-understanding fac-tors influenced significantly on social responsibility factors. As such, it was found that Taekonwdo training influ-enced leadership skill and community spirit.

Prediction of the future location of vehicles and other mobile targets is instrumental in intelligent transportation system applications. In fact, networking schemes and protocols based on machine learning can benefit from the results of such accurate trajectory predictions. This is because routing decisions always need to be made for the future scenario due to the inevitable latency caused by the processing and propagation of the routing request and response. Thus, to predict the high-precision trajectory beyond the state of the art, we propose a generative adversarial network (GAN)-based vehicle trajectory prediction method, GAN-VEEP, for urban roads. The proposed method consists of three components: 1) vehicle coordinate transformation for data set preparation; 2) neural network prediction model trained by GAN; and 3) vehicle turning model to adjust the prediction process. The vehicle coordinate transformation model is introduced to deal with the complex spatial dependence in the urban road topology. Then, the neural network prediction model learns from the behavior of vehicle drivers. Finally, the vehicle turning model can refine the driving path based on the driver’s psychology. Compared with its counterparts, the experimental results show that GAN-VEEP exhibits higher effectiveness in terms of the average accuracy, mean absolute error, and root-mean-squared error.

This concept paper will discuss the factors that may have an impact on the player's performance in achieving an elite level within the context of football. There are many factors that influence the development and performance of football players in reaching elite levels. These include physical, technical, tactical, psychological and social factors. In terms of social components, parents, siblings, teachers, coaches, training facilities, and the environment are factors that may influence performance. Therefore, the primary aim of this concept paper is to investigate the impact of social and environmental support factors on elite players, particularly in football. Previous research has found that social factors such as parental and coach support may influence the player’s performance in reaching the elite level. Additionally, another factor that is still debated is the role of the training environment for football players. Suitable and conducive facilities and environments have been found to improve the player’s performance in achieving the elite level. The findings obtained will help in producing a conceptual framework of social support factors and training environment facilities that play an important role in influencing athlete performance in football.

The purpose of this study is to determine factors such as psychological factors, social factors, physical factors and financial factors that affect work satisfaction of Civil Servants in Bappeda Office of Seluma Regency. The sample in this study was 27 Civil Servants in Bappeda Office of Seluma Regency. The sampling technique used in the study was a census because all populations were sampled. Collecting data using a questionnaire and the method of analysis used is multiple linear regression, test of determination and hypothesis testing. The results showed a positive regression direction with the regression equation Y = 6.702 + 0.438X1 + 0.344 X2 + 0.146X3 + 0.638X4. Psychological factors have a positive and significant influence on work satisfaction of civil servant in Bappeda Office of Seluma Regency with a significant value of 0.023 which is small from 0.05. Social factors indicate a positive and significant influence on work satisfaction of civil servant in Bappeda Office of Seluma Regency with a significant value of 0.002 less than 0.05. Physical factors have a positive and significant influence on work satisfaction of civil servant in Bappeda Office of Seluma Regency with a significant value of 0.027, less than 0.05. Financial factors have a positive and significant effect on work satisfaction of civil servant in Bappeda Office of Seluma Regency with a significant value of 0.000, less than 0.05. Psychological factors, social factors, physical factors and financial factors have a significant and joint influence on performance of civil servant in Bappeda Office of Seluma Regency with a significant value of 0.000 is smaller than 0.05. This illustrates that if there is attention to psychological factors, social factors, physical factors and financial factors, civil servant satisfaction will increase

Psoriasis is a disease state that may present significant cumulative life course impairment (CLCI). The impact of psoriasis on CLCI can be divided into social factors such as stigmatization, psychological factors such as depression, and physical factors such as pruritis, pain and arthritis. With a bimodal age range at first presentation, psoriasis tends to affect those in the second and fifth decades of life. In accordance with the CLCI model, the age of first presentation may substantially affect an individuals' life course, with younger patients more susceptible to CLCI. Social, psychological, and physical factors also provide protection from CLCI: personality, coping mechanisms, social support, and treatment or therapy may act as positive factors and mitigate these damaging effects. As the time course of most clinical trials encompasses a fraction of a patients' life, the true nature of this impact has not been easily captured. Longitudinal CLCI data in psoriasis is limited and continued life course data is needed.

A mean field game approach for a class of linear quadratic discrete choice problems with congestion avoidance

SINRAT is a computer program for reconstruction of traffic accidents, one that constitutes a powerful tool in the calculation applicable to the investigation, reconstruction and analysis of the damage produced in traffic accidents. SINRAT is provided with an input data pre–processor that allows the introduction of all the factors involved in an accident like braking, acceleration and steering manoeuvres executed by drivers, road profile, etc. SINRAT includes a database where the technical features of about 7000 vehicles are found, so that when it is necessary to reconstruct an accident, you just have to indicate the make and model of the implicated vehicles. SINRAT incorporates a simulation model of the behaviour of vehicles using the bond graph technique. Each vehicle is considered as a three–dimensional body, linked to the wheels through the suspension system. The tyre–road contact is also modelled. The collision model used permits simulation of the behaviour of the vehicles before, during and after the collision. This collision takes into account also the stiffness of the car's body and its energy absorption during the collision. SINRAT incorporates a driver model that determines the steering manoeuvre so that the vehicle traces a prearranged trajectory. It incorporates also the possibility to introduce the real profile of the road when it refers to the raisings, ramps, transition curves, etc. Even more, it includes an algorithm for the automatic reconstruction of traffic accidents, which permits calculation of vehicle velocity from the data at the scene of the accident. Starting from these data, the program reconstructs the accident varying the collision velocities until it reproduces the point of collision as well as the final positions of all vehicles. Lastly, SINRAT possesses a graphic post–processor which permits the visualisation of the movements of the vehicles and the visualisation of variables in terms of x–y plots.

In the field of trajectory prediction, when new scene data is continuously introduced, the system may forget the historical trajectory information that has been learned before, leading to the phenomenon of decreasing the prediction accuracy of previous scenes, which is called catastrophic forgetting. The Multi-Memo Net framework proposed in this paper is an instance-based approach that stores typical trajectories through a memory bank thereby establishing a direct link between the current and historical scenes. During training, self-encoders and decoders are used to efficiently memorize the feature expressions of past trajectories and future intentions; during prediction, the controller finds similar scenes that have occurred in history in the memory bank based on the past trajectories and contextual information for trajectory prediction, and ultimately obtains a multimodal trajectory prediction through K-means clustering, and while predicting, the model can keep updating the content of the memory bank to learn, thus iteratively optimizing the model prediction performance. Thus, the model prediction performance is iteratively optimized. Compared with baseline models such as Kalman filter and Memory Augmented Networks for Multiple Trajectory Prediction (MANTRA) model, the method in this paper has significant improvement in Average Displacement Error (ADE) and Final Displacement Error (FDE) metrics.

Background: Physical activity plays a crucial role in children's health and well-being. Active school commuting (ASC), one of the strategies to enhance physical activity among children, has declined globally. However, no data is available for Indonesian children. None of the determinants of children’s ASC has been examined in Indonesian studies. Objectives: This study aimed to 1) measure the ASC rate and 2) analyze the association between individual, social, and physical environmental factors, and the ASC rate among primary school children in three urban areas in Indonesia (South Jakarta, Central Jakarta, and South Tangerang). Methods: This is a cross-sectional study using an online survey completed by mothers as representatives of their children. The survey was completed by 441 parents from 9 primary schools in South Jakarta, Central Jakarta, and South Tangerang. Results: 1) Only 28.3% of children engage in ASC (walking or cycling), 2) individual factor (‘do not dare to go to school alone’), social factors (‘having a friend for going to school’ and ‘afraid of street crime’), and environmental factors (inadequacy of public transport, broken roads, and school distance) are significantly associated with ASC. Conclusion: less than one-third of primary school children in South Jakarta, Central Jakarta, and South Tangerang walk or bike to go to and back from school. Perceived individual, social, and environmental factors might hinder active school commuting among children. Future interventions need to attenuate negative perceptions toward ASC from individual, social, and environmental perspectives.

Pedestrian trajectory prediction is fundamental to a wide range of scientific research work and industrial applications. Most of the current advanced trajectory prediction methods incorporate context information such as pedestrian neighbourhood, labelled static obstacles, and the background scene into the trajectory prediction process. In contrast to these methods which require rich contexts, the method in our paper focuses on predicting a pedestrian's future trajectory using his/her observed part of the trajectory only. Our method, which we refer to as LVTA, is a Location-Velocity-Temporal Attention LSTM model where two temporal attention mechanisms are applied to the hidden state vectors from the location and velocity LSTM layers. In addition, a location-velocity attention layer embedded inside a tweak module is used to improve the predicted location and velocity coordinates before they are passed to the next time step. Extensive experiments conducted on three large benchmark datasets and comparison with eleven existing trajectory prediction methods demonstrate that LVTA achieves competitive prediction performance. Specifically, LVTA attains 9.19 pixels Average Displacement Error (ADE) and 17.28 pixels Final Displacement Error (FDE) for the Central Station dataset, and 0.46 metres ADE and 0.92 metres FDE for the ETH&UCY datasets. Furthermore, evaluation on using LVTA to generate trajectories of different prediction lengths and on new scenes without the need of retraining confirms that it has good generalizability.

This article introduces a novel model for low-quality pedestrian trajectory prediction, the social nonstationary transformers (NSTransformers), that merges the strengths of NSTransformers and spatiotemporal graph transformer (STAR). The model can capture social interaction cues among pedestrians and integrate features across spatial and temporal dimensions to enhance the precision and resilience of trajectory predictions. We also propose an enhanced loss function that combines diversity loss with logarithmic root mean squared error (log-RMSE) to guarantee the reasonableness and diversity of the generated trajectories. This design adapts well to complex pedestrian interaction scenarios, thereby improving the reliability and accuracy of trajectory prediction. Furthermore, we integrate a generative adversarial network (GAN) to model the randomness inherent in pedestrian trajectories. Compared to the conventional standard Gaussian distribution, our GAN approach better simulates the intricate distribution found in pedestrian trajectories, enhancing the trajectory prediction's diversity and robustness. Experimental results reveal that our model outperforms several state-of-the-art methods. This research opens the avenue for future exploration in low-quality pedestrian trajectory prediction.

BackgroundThe ageing of the working population and the sustainability of work throughout the life cycle represent a significant challenge for many European countries, particularly in relation to the implementation of legislation raising the retirement age.ObjectiveThe objective of this study was to examine the physical, psychological and social risk and protective factors that influence the sustainability of work during the ageing process.MethodsTwenty-five interviews were conducted, followed by a reflexive thematic analysis, with the aim of gathering the perspectives of a company's employees regarding factors related to ageing in the workplace.ResultsTwo key themes emerged from the analysis, encapsulating the participants' different perceptions of risk and protective factors. Among the physical risk factors were those related to stress caused by job characteristics, which affect physical health. In addition, the study identified continuous shift work as a significant risk factor, which affects both physical health and the ability to reconcile work and family life. In addition, the responsibility of caring for dependent elderly family members and childcare responsibilities were highlighted as social factors that may affect employees' well-being.ConclusionsThe study provides a useful basis for the implementation of company interventions to improve the work sustainability of older employees, with possible applications in other similar companies.

Neurological and psychiatric disorders are a burden on social and economic resources. Therefore, maintaining brain health and preventing these disorders are important. While the physiological functions of the brain are well studied, few studies have focused on keeping the brain healthy from a neuroscientific viewpoint. We propose a magnetic resonance imaging (MRI)-based quotient for monitoring brain health, the Brain Healthcare Quotient (BHQ), which is based on the volume of gray matter (GM) and the fractional anisotropy (FA) of white matter (WM). We recruited 144 healthy adults to acquire structural neuroimaging data, including T1-weighted images and diffusion tensor images, and data associated with both physical (BMI, blood pressure, and daily time use) and social (subjective socioeconomic status, subjective well-being, post-materialism and Epicureanism) factors. We confirmed that the BHQ was sensitive to an age-related decline in GM volume and WM integrity. Further analysis revealed that the BHQ was critically affected by both physical and social factors. We believe that our BHQ is a simple yet highly sensitive, valid measure for brain health research that will bridge the needs of the scientific community and society and help us lead better lives in which we stay healthy, active, and sharp.

The World Health Organization defines health as a state of physical, mental and social well being. This study was conducted to explore chronological relationships between physical, mental and social factors. Among urban-dwelling elderly aged 65 years and over, data were collected via a self-report questionnaire in 2001 and 2004. The three health-related latent factors were identified with nine measurement variables by an exploratory factor analysis. A structural equation modeling method was used to analyze underlying relationships among the three factors with a cross-lagged model and a synchronous model. A total of 7,683 individuals aged between 65 and 84 years were analyzed. The three-year prior and current physical health significantly affected social health as well as mental health, and this effect appeared to be stronger in males compared to females. Maintenance of physical health may be crucial to support mental and social health among elderly individuals.