Smart Traffic Planning and Analytics, Autonomous Mobility Technologies, and Algorithm-driven Sensing Devices in Urban Transportation Systems.

AuthorGriffin, Karen
  1. Introduction

    Self-driving car perception systems will completely remove human error, and thus nearly all traffic accidents, considerably enhancing automotive safety through autonomous driving algorithms and behaviors. (Thomas and Groth, 2021) Path planning and perception mapping leverage machine learning and control algorithms in addition to sensory data to circumvent collisions. (Lee et al., 2021) Lack of knowledge is associated with safety issues and apprehension of transferring control to a self-driving car. (Deruyttere et al., 2021)

  2. Conceptual Framework and Literature Review

    Demographics and personality shape technology expectations and autonomous vehicle acceptance and adoption. (Zhang et al., 2021) Self-driving vehicle applications monitor car operations and enhance travel safety in multi-modal transportation systems. (Nordstrom and Engholm, 2021) Computer vision tasks configured by use of highly tuned convolutional neural networks, raw image processing and rule-based logic systems, and machine/deep learning algorithms are pivotal in autonomous driving. (Gupta et al., 2021) Selfdriving cars can carry out accurate localization and perform collision-free routeways by deploying high-definition maps that supply precise road environment data gathered by smart connected devices. (Kim et al., 2021) By detecting and monitoring in-vehicle sensors localization reliability is optimized. (Seo et al., 2021) Self-driving systems may encounter inevitable crash incidents, but the sensor-based road settings can refashion moral dilemma as risk analysis in keeping with algorithmic decision-making. (Lucifora et al., 2021) Efficient and precise depth map assessments assists computer vision systems pivotal in self-driving vehicles. (Thompson et al., 2021) Predictive control is decisive in uncertain environments where autonomous vehicles and human-driven cars share the road, algorithmic decision-making optimizing traffic safety and smooth driving. (Tran and Bae, 2021)

  3. Methodology and Empirical Analysis

    Using and replicating data from AAA, ANSYS, Atomik Research, AUVSI, Axios, Charles Koch Institute, Deloitte, eMarketer, Future Agenda, HNTB, INRIX, Kennedys, McKinsey, OpinionWay, and Perkins Coie, we performed analyses and made estimates regarding how self-driving cars can carry out accurate localization and can learn to enhance their behaviors through deep learning technologies. The results of a study based on data collected from 6,300 respondents provide support for our research model. Descriptive statistics of compiled data from the completed surveys were calculated when appropriate.

  4. Study Design, Survey Methods, and Materials

    The interviews were conducted online and data were weighted by five variables (age, race/ethnicity, gender, education, and geographic region) using the Census Bureau's American Community Survey to reflect reliably and accurately the demographic composition of the United States.

    Data sources: AAA, ANSYS, Atomik Research, AUVSI, Axios, Charles Koch Institute, Deloitte, eMarketer, Future Agenda, HNTB, INRIX, Kennedys, McKinsey, OpinionWay, and Perkins Coie. Study participants: 6,300 individuals provided an informed e-consent.

    All data were interrogated by employing graphical and numeric exploratory data analysis methods. Results are estimates and commonly are dissimilar within a narrow range around the actual value. Multivariate analyses, and not univariate associations with outcomes, are more likely to factor out confounding covariates and more precisely determine the relative significance of individual variables. The data was weighted in a multistep process that accounts for multiple stages of sampling and nonresponse that occur at different points in the survey process.

    Test data was populated and analyzed in SPSS to ensure the logic and randomizations were working as intended before launching the survey. To ensure high-quality data, data quality checks were performed to identify any respondents showing clear patterns of satisficing (e.g., checking for high rates of leaving questions blank). Sampling errors and test of statistical significance take into account the effect of weighting. Question wording and practical difficulties in conducting surveys can introduce error or bias into the findings of opinion polls. The sample weighting was accomplished using an iterative proportional fitting process that simultaneously balanced the distributions of all variables. Stratified sampling methods were used and weights were trimmed not to exceed 3. Average margins of error, at the 95% confidence level, are +/-2%. The design effect for the survey was 1.3. For tabulation purposes, percentage points are rounded to the nearest whole number. The cumulative response rate accounting for non-response to the recruitment surveys and attrition is 2.5%.

    The precision of the online polls was measured using a Bayesian credibility interval. Addressing a significant knowledge gap in the literature, the research has complied with stringent methodology, reporting, and data analysis requirements. Confirmatory factor analysis was employed to test for the reliability and validity of measurement instruments.

    Flow diagram of study procedures

  5. Statistical Analysis

    Descriptive analyses (mean and standard deviations for continuous variables and counts and percentages for categorical variables) were used. Descriptive statistical analysis and multivariate inferential tests were undertaken for the survey responses and for the purpose of variable reduction in regression modeling. This survey employs statistical weighting procedures to clarify deviations in the survey sample from known population features, which is instrumental in correcting for differential survey participation and random variation in samples. Independent t-tests for continuous variables or chisquare tests for categorical variables were employed.

    Descriptive and inferential statistics provide a summary of the responses and comparisons among subgroups. Mean and standard deviation, t-test, exploratory factor analysis, and data normality were inspected using SPSS. To ensure reliability and accuracy of data, participants undergo a rigorous verification process and incoming data goes through a sequence of steps and multiple quality checks. AMOS-SEM analyzed the full measurement model and structural model. The break-off rate among individuals who logged onto the survey and completed at least one item is 0.2%.

    An Internet-based survey software program was utilized for the delivery and collection of responses. Groundbreaking computing systems and databases enable data gathering and processing, extracting meaning through robust deployment. Panel research represents a swift method for gathering data recurrently, drawing a sample from a pre-recruited set of respondents. Behavioral datasets have been collected, entered into a spreadsheet, and cuttingedge computational techniques and empirical strategies have been harnessed for analysis. Non-response bias and common method bias, composite reliability, and...

To continue reading

Request your trial

VLEX uses login cookies to provide you with a better browsing experience. If you click on 'Accept' or continue browsing this site we consider that you accept our cookie policy. ACCEPT