Dataset Information

Detection of Driving Capability Degradation for Human-Machine Cooperative Driving.

ABSTRACT: Due to the limitation of current technologies and product costs, humans are still in the driving loop, especially for public traffic. One key problem of cooperative driving is determining the time when assistance is required by a driver. To overcome the disadvantage of the driver state-based detection algorithm, a new index called the correction ability of the driver is proposed, which is further combined with the driving risk to evaluate the driving capability. Based on this measurement, a degraded domain (DD) is further set up to detect the degradation of the driving capability. The log normal distribution is used to model the boundary of DD according to the bench test data, and an online algorithm is designed to update its parameter interactively to identify individual driving styles. The bench validation results show that the identification algorithm of the DD boundary converges finely and can reflect the individual driving characteristics. The proposed degradation detection algorithm can be used to determine the switching time from manual to automatic driving, and this DD-based cooperative driving system can drive the vehicle in a safe condition.

SUBMITTER: Gao F

PROVIDER: S-EPMC7181156 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Detection of Driving Capability Degradation for Human-Machine Cooperative Driving.

Gao Feng F He Bo B He Yingdong Y

Sensors (Basel, Switzerland) 20200401 7

Due to the limitation of current technologies and product costs, humans are still in the driving loop, especially for public traffic. One key problem of cooperative driving is determining the time when assistance is required by a driver. To overcome the disadvantage of the driver state-based detection algorithm, a new index called the correction ability of the driver is proposed, which is further combined with the driving risk to evaluate the driving capability. Based on this measurement, a degr ...[more]

PMID: 32244626

Similar Datasets

Project description:BackgroundIn biomedicine, machine learning (ML) has proven beneficial for the prognosis and diagnosis of different diseases, including cancer and neurodegenerative disorders. For rare diseases, however, the requirement for large datasets often prevents this approach. Huntington's disease (HD) is a rare neurodegenerative disorder caused by a CAG repeat expansion in the coding region of the huntingtin gene. The world's largest observational study for HD, Enroll-HD, describes over 21,000 participants. As such, Enroll-HD is amenable to ML methods. In this study, we pre-processed and imputed Enroll-HD with ML methods to maximise the inclusion of participants and variables. With this dataset we developed models to improve the prediction of the age at onset (AAO) and compared it to the well-established Langbehn formula. In addition, we used recurrent neural networks (RNNs) to demonstrate the utility of ML methods for longitudinal datasets, assessing driving capabilities by learning from previous participant assessments.ResultsSimple pre-processing imputed around 42% of missing values in Enroll-HD. Also, 167 variables were retained as a result of imputing with ML. We found that multiple ML models were able to outperform the Langbehn formula. The best ML model (light gradient boosting machine) improved the prognosis of AAO compared to the Langbehn formula by 9.2%, based on root mean squared error in the test set. In addition, our ML model provides more accurate prognosis for a wider CAG repeat range compared to the Langbehn formula. Driving capability was predicted with an accuracy of 85.2%. The resulting pre-processing workflow and code to train the ML models are available to be used for related HD predictions at: https://github.com/JasperO98/hdml/tree/main .ConclusionsOur pre-processing workflow made it possible to resolve the missing values and include most participants and variables in Enroll-HD. We show the added value of a ML approach, which improved AAO predictions and allowed for the development of an advisory model that can assist clinicians and participants in estimating future driving capability.

Project description:Background: Cardiac pacemaking remains an unsolved matter from many perspectives. Extensive experimental and computational studies have been performed to describe the sinoatrial physiology across different scales, from the molecular to clinical levels. Nevertheless, the mechanism by which a heartbeat is generated inside the sinoatrial node and propagated to the working myocardium is not fully understood at present. This work aims to provide quantitative information about this fascinating phenomenon, especially regarding the contributions of cellular heterogeneity and fibroblasts to sinoatrial node automaticity and atrial driving. Methods: We developed a bidimensional computational model of the human right atrial tissue, including the sinoatrial node. State-of-the-art knowledge of the anatomical and physiological aspects was adopted during the design of the baseline tissue model. The novelty of this study is the consideration of cellular heterogeneity and fibroblasts inside the sinoatrial node for investigating the manner by which they tune the robustness of stimulus formation and conduction under different conditions (baseline, ionic current blocks, autonomic modulation, and external high-frequency pacing). Results: The simulations show that both heterogeneity and fibroblasts significantly increase the safety factor for conduction by more than 10% in almost all the conditions tested and shorten the sinus node recovery time after overdrive suppression by up to 60%. In the human model, especially under challenging conditions, the fibroblasts help the heterogeneous myocytes to synchronise their rate (e.g. -82% in σCL under 25 nM of acetylcholine administration) and capture the atrium (with 25% L-type calcium current block). However, the anatomical and gap junctional coupling aspects remain the most important model parameters that allow effective atrial excitations. Conclusion: Despite the limitations to the proposed model, this work suggests a quantitative explanation to the astonishing overall heterogeneity shown by the sinoatrial node.

Project description:BackgroundBrucellosis is a common zoonotic infectious disease in China. This study aimed to investigate the incidence trends of brucellosis in China, construct an optimal prediction model, and analyze the driving role of climatic factors for human brucellosis.MethodsUsing brucellosis incidence, and the socioeconomic and climatic data for 2014-2020 in China, we performed spatiotemporal analyses and calculated correlations with brucellosis incidence in China, developed and compared a series of regression and Seasonal Autoregressive Integrated Moving Average X (SARIMAX) models for brucellosis prediction based on socioeconomic and climatic data, and analyzed the relationship between extreme weather conditions and brucellosis incidence using copula models.ResultsIn total, 327,456 brucellosis cases were reported in China in 2014-2020 (monthly average of 3898 cases). The incidence of brucellosis was distinctly seasonal, with a high incidence in spring and summer and an average annual peak in May. The incidence rate was highest in the northern regions' arid and continental climatic zones (1.88 and 0.47 per million people, respectively) and lowest in the tropics (0.003 per million people). The incidence of brucellosis showed opposite trends of decrease and increase in northern and southern China, respectively, with an overall severe epidemic in northern China. Most regression models using socioeconomic and climatic data cannot predict brucellosis incidence. The SARIMAX model was suitable for brucellosis prediction. There were significant negative correlations between the proportion of extreme weather values for both high sunshine and high humidity and the incidence of brucellosis as follows: high sunshine, [Formula: see text] = -0.59 and -0.69 in arid and temperate zones; high humidity, [Formula: see text] = -0.62, -0.64, and -0.65 in arid, temperate, and tropical zones.ConclusionsSignificant seasonal and climatic zone differences were observed for brucellosis incidence in China. Sunlight, humidity, and wind speed significantly influenced brucellosis. The SARIMAX model performed better for brucellosis prediction than did the regression model. Notably, high sunshine and humidity values in extreme weather conditions negatively affect brucellosis. Brucellosis should be managed according to the "One Health" concept.

Dataset Information

Detection of Driving Capability Degradation for Human-Machine Cooperative Driving.

Publications

Detection of Driving Capability Degradation for Human-Machine Cooperative Driving.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets