Engineering Commons^™

Physical Information Incorporated Clustering Techniques And Their Applications In Transportation Information System, Yang Zhang

Doctoral Dissertations

Massive data from different sources are becoming available in transportation field, and spurring new research on utilizing these data to nurture new intelligent transportation information systems. Clustering algorithms are among the methods that are being applied to the domain but facing challenges. Classical clustering algorithms work fine with \point" based data, which are homogeneous and have no extra constraints. Data in transportation are sometimes involved with specific geometric shapes, have underlying constraints, and can be heterogeneous. There has been no clustering algorithm dedicated to these situations.

In this dissertation, we re-examine the mathematical foundation and underlying philosophy of hierarchical, density …

Evaluation Of Increased Targeted Enforcement And Community-Based Outreach And Education Programs To Increase Nighttime Seatbelt Use In East Tennessee, Kwaku Frimpong Boakye

Doctoral Dissertations

According to the National Highway Traffic Safety Administration (NHTSA), motor vehicle crashes are the leading cause of death among people aged 1-54 in the United Sates. In 2015, the number of motor-vehicle deaths on U.S. roadways totaled 35,092, a 7% increase from 2014 (32,744). Though lower gas prices and increased vehicle mileage combined with risky driving behaviors (e.g. speeding, driving while texting) account for the increased fatality rate, seatbelt non-use has been a significant contributory factor. It is estimated that nearly half (48%) of passenger vehicle occupants involved in fatal crashes each year are unrestrained.

In a recent 2014 report …

Errors And Truths From Transportation Data Aggregation: Some Implications For Research And Practice, Hyeonsup Lim

Doctoral Dissertations

Data aggregation, which is a process to combine information by defined groups for statistical analysis, summary, data size reduction, or other purposes, has fundamental challenges, such as loss of the original information. Improper data aggregation, such as sampling bias or incorrect calculation of average, may cause misreading of information. In first chapter, it is revealed that the harmonic mean, which is used to calculate space mean speed for fixed segment, has a sampling bias, i.e., overestimation with small samples. The several impact analyses show that the sampling bias is affected by sampling rate, time interval, segment length, and distribution type. …