working paper

Death on the Crosswalk: A Study of Pedestrian-Automobile Collisions in Los Angeles

Publication Date

April 1, 2005

Author(s)

Anastasia Loukaitou-Sideris

Areas of Expertise

Infrastructure Delivery, Operations, & Resilience Safety, Public Health, & Mobility Justice

View working paper

Abstract

This research explores the spatial distribution of pedestrian-automobile collisions in Los Angeles and analyzes the social and physical factors that affect the risk of getting involved in such accidents. More specifically, this study investigates the influence of socio-demographic, land use, density, and traffic characteristics on pedestrian accident rates.

We first provide an exploratory spatial and statistical analysis of pedestrian collision data in the city of Los Angeles to identify preliminary relationships between accident frequency and socio-demographic and land use characteristics at the census tract and block group levels. This aggregate level analysis also helps us identify major concentrations of pedestrian collision data which are used at a second stage of the research for more qualitative and detailed analysis of specific case studies of intersections with high frequency of pedestrian-automobile accidents. The study uses pedestrian accident data provided by the Los Angeles Department of Transportation, traffic volume data provided by Caltrans, socio-demographic data from the U.S. Census 2000, land use data from the Southern California Association of Governments (SCAG), and pedestrian volume and built environment data from fieldwork research.

published journal article

Norm approximation method for handling traffic count inconsistencies in path flow estimator

Transportation Research Part B: Methodological

Publication Date

September 1, 2009

Author(s)

Anthony Chen, Piya Chootinan, Will Recker

View published journal article

Suggested Citation

Anthony Chen, Piya Chootinan and Will Recker (2009) “Norm approximation method for handling traffic count inconsistencies in path flow estimator”, Transportation Research Part B: Methodological, 43(8-9), pp. 852–872. Available at: 10.1016/j.trb.2009.02.007.

conference paper

Event-based communication strategy for collaborative navigation with signals of opportunity

2018 52nd asilomar conference on signals, systems, and computers

Publication Date

October 1, 2018

Author(s)

Joshua Morales, Zaher Kassas

View conference paper

Suggested Citation

Joshua Morales and Zaher M. Kassas (2018) “Event-based communication strategy for collaborative navigation with signals of opportunity”, in 2018 52nd asilomar conference on signals, systems, and computers. IEEE, pp. 548–553. Available at: 10.1109/acssc.2018.8645193.

MS Thesis

The influence of land use and network structure on travel behavior

Publication Date

June 30, 1996

Author(s)

Anup Kulkarni

Areas of Expertise

Travel Behavior, Land Use, & the Built Environment

View MS Thesis

Suggested Citation

Anup Kulkarni (1996) The influence of land use and network structure on travel behavior. MS Thesis. UC Irvine. Available at: https://uci.primo.exlibrisgroup.com/permalink/01CDL_IRV_INST/17uq3m8/alma991018605649704701.

Preprint Journal Article

Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective

Publication Date

September 15, 2024

Author(s)

Ningfei Wang, Shaoyuan Xie, Takami Sato, Yunpeng Luo, Kaidi Xu, Qi Alfred Chen

Areas of Expertise

Intelligent Transportation Systems, Emerging Technologies, & Big Data

View Preprint Journal Article

Abstract

Traffic Sign Recognition (TSR) is crucial for safe and correct driving automation. Recent works revealed a general vulnerability of TSR models to physical-world adversarial attacks, which can be low-cost, highly deployable, and capable of causing severe attack effects such as hiding a critical traffic sign or spoofing a fake one. However, so far existing works generally only considered evaluating the attack effects on academic TSR models, leaving the impacts of such attacks on real-world commercial TSR systems largely unclear. In this paper, we conduct the first large-scale measurement of physical-world adversarial attacks against commercial TSR systems. Our testing results reveal that it is possible for existing attack works from academia to have highly reliable (100%) attack success against certain commercial TSR system functionality, but such attack capabilities are not generalizable, leading to much lower-than-expected attack success rates overall. We find that one potential major factor is a spatial memorization design that commonly exists in today’s commercial TSR systems. We design new attack success metrics that can mathematically model the impacts of such design on the TSR system-level attack success, and use them to revisit existing attacks. Through these efforts, we uncover 7 novel observations, some of which directly challenge the observations or claims in prior works due to the introduction of the new metrics.

Suggested Citation

Ningfei Wang, Shaoyuan Xie, Takami Sato, Yunpeng Luo, Kaidi Xu and Qi Alfred Chen (2024) “Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective”. arXiv. Available at: 10.14722/ndss.2025.23090.

working paper

Autos, Transit and the Sprawl of Los Angeles: The 1920s

Publication Date

March 1, 1984

Author(s)

Martin Wachs

Working Paper

UCI-ITS-WP-84-2

View working paper

Abstract

The dispersed, low-density land-use pattern that has come to be associated with Los Angeles has roots in two periods of economic growth during which critical choices were made. While many observers associate the sprawl of Los Angeles with the freeway building program following World War II, the pattern was quite well established prior to 1930. It can be traced to an early period of dispersed growth, from 1880 to 1910, when inter-urban street railways allowed residential decentralization. The pattern was reinforced during the boom of the nineteen twenties, when rapid growth was accompanied by dramatic shifts in travel patterns and industrial location, partly in response to the automobile. This paper examines changes during these periods in the context of a continuing preference for low density living, and reviews the planning policies and political decisions of the twenties, when a comprehensive highway program was adopted, but a regional rapid transit plan failed to gain acceptance.

Suggested Citation

Martin Wachs (1984) Autos, Transit and the Sprawl of Los Angeles: The 1920s. Working Paper UCI-ITS-WP-84-2. Institute of Transportation Studies, Irvine. Available at: https://escholarship.org/uc/item/7wq9b14d.

published journal article

California households' willingness to pay for `green' electronics

Journal of Environmental Planning and Management

Publication Date

January 1, 2007

Author(s)

Jean-Daniel Saphores, Hilary Nixon, Oladele Ogunseitan, Andrew A. Shapiro

View published journal article

Abstract

Concerns about rapid increases in the volume of electronic waste (e-waste) and its potential toxicity have sharpened policy makers’ interest for extended producer responsibility to encourage manufacturers of consumer electronic devices (CEDs) to `design for the environment’. This paper examines consumer willingness to pay for `green’ electronics based on a 2004 mail survey of California households. Using ordered logit models, it was found that significant predictors of willingness to pay for `greener’ computers and cell phones include age, income, education, beliefs about the role of government for improving environmental quality, as well as environmental attitudes and behaviors, but neither gender nor political affiliation. Although most respondents are willing to pay only a 1% premium for `greener’ CEDs, innovation and EU directives may soon make them competitive with conventional CEDs.

Suggested Citation

Jean-Daniel M. Saphores, Hilary Nixon, Oladele A. Ogunseitan and Andrew A. Shapiro (2007) “California households' willingness to pay for `green' electronics”, Journal of Environmental Planning and Management, 50(1), pp. 113–133. Available at: 10.1080/09640560601048549.

working paper

Toward a Dynamic Model of Individual Activity Pattern Formulation

Publication Date

July 1, 1981

Author(s)

Gregory Root, Will Recker

Working Paper

UCI-ITS-WP-81-4, UCI-ITS-AS-WP-81-2

Areas of Expertise

Travel Behavior, Land Use, & the Built Environment

View working paper

Abstract

This paper presents preliminary thoughts on the development of a theoretical model of complex travel/activity behavior that incorporates both spatial and temporal constraints. The theoretical model is based on the use of individual activity patterns to represent complex travel/ activity behavior and assumes the form of a stochastic multiobjective dynamic programming model. A multiobjective dynamic programming approach is utilized due to the presence of conflicting objectives and the influence that past activity/travel decisions have on future choices.

Suggested Citation

Gregory S. Root and Will Recker (1981) Toward a Dynamic Model of Individual Activity Pattern Formulation. Working Paper UCI-ITS-WP-81-4, UCI-ITS-AS-WP-81-2. Institute of Transportation Studies, Irvine. Available at: https://escholarship.org/uc/item/7t72q459.

Phd Dissertation

Neural network models for automated detection of lane-blocking incidents on freeways

Publication Date

June 30, 1994

Associated Project

Neural Network Models for Automated Detection of Non-Recurring Congestion

Author(s)

Kelvin Cheu

Areas of Expertise

Intelligent Transportation Systems, Emerging Technologies, & Big Data

View Phd Dissertation

Abstract

A major source of urban freeway delay in the United States is non-recurring congestion caused by incidents such as accidents, disabled vehicles, spilled loads, temporary maintenance and construction activities, signal and detector malfunctions, and other special and unusual events that disrupt the normal flow of traffic. The automated detection of freeway incidents is an important function of a freeway traffic management center. Early detection of incidents is vital for formulating effective response strategies such as timely dispatch of emergency services and incident removal crews, control and routing of traffic around the incident location, and provision of real-time traffic information to motorists. A number of incident detection algorithms, based on conventional approaches, have been developed over the past several decades, and a few of them are being deployed at urban freeway systems in major cities. These conventional algorithms have met with varying degree of success in their detection performance. In this research, a new incident detection technique based on an artificial neural network approach has been proposed. The objective of this research was to demonstrate the use of artificial neural network models for automated detection of lane-blocking incidents on urban freeways. The study focused on the application of neural network models in classifying traffic surveillance data obtained from inductive loop detectors, and the use of the classified output to detect an incident. Three types of neural network models were developed to detect lane-blocking incidents: the multi-layer feed-forward neural network, self-organizing feature map and adaptive resonance theory 2. The models were developed with simulation data from a study site and tested with both simulation and field data at the study site and other locations. The multi-layer feed-forward neural network was found to have the highest potential among the four models to achieve a better incident detection performance. This network consistently detected most of the lane-blocking incidents and gave a false alarm rate lower than the conventional algorithms currently in use. The results have demonstrated the potential of artificial neural network models in improving incident detection performance over currently available techniques.

Suggested Citation

Kelvin Cheu (1994) Neural network models for automated detection of lane-blocking incidents on freeways. PhD Dissertation. UC Irvine. Available at: https://uci.primo.exlibrisgroup.com/permalink/01CDL_IRV_INST/1go3t9q/alma991035092925704701.

Related Publications

research report | Sep 1993

Neural Network Models For Automated Detection Of Non-recurring Congestion

Phd Dissertation

Activity-based travel demand model with time-use and microsimulation incorporating intra-household interactions

Publication Date

January 1, 2008

Associated Project

A Household Activity Scheduling Model Incorporating A Task Allocation Process With Week-Based Learning Mechanisms

Author(s)

Hee-Kyung Kim

Areas of Expertise

Travel Behavior, Land Use, & the Built Environment

View Phd Dissertation

Abstract

The activity-based travel demand model recognizes that travel is derived from the demand for activity participation distributed in space. The focus on intra-household interactions and linkages between people’s behavior and social and physical environment has been identified as emerging features of the activity-based approach that would be important to travel behavior research. The dissertation is dedicated to an in-depth exploration of the within-household interactions by theoretical specification and empirical development of the household activity time allocation models based on a utility maximization framework with the household as the unit of analysis. Furthermore, the dissertation also aims to propose a model of the household activity scheduling process primarily focusing on task allocation mechanisms on the basis of the human agents adjusting themselves to the built social and physical environment. Development of the activity time allocation model in this dissertation includes two types of structural time allocation models. First, the collective models based on two assumptions that household heads have their own utility functions and that decisions by them reach Pareto-efficient outcomes are introduced to develop intra-household activity time allocation models for leisure demand and housework activity. Secondly, intra-household time allocation to housework activity is further examined through the estimation of time allocation to the different types of activities by the different types of household members along with extensive exploration of various theories and identification of related interactions. This dissertation proposes a household activity scheduling process with a model design based on a weekly pattern system, which is expected to keep various advantages compared to a deterministic daily model system. Along with learning and adaptation procedures, the human being as a learning agent is designed to prepare strategic schedules of behavior to achieve individual goals through interactive environments, and implement those plans via activity execution. At the household level, the household and its members as decision agents are also designed to optimize the allocation of the available household labor resource under the presence of the uncertainties of the physical and social environments. After describing the mathematical framework and solution procedure, a simulation experiment is conducted within a hypothetical environment to demonstrate how the proposed model works.

Suggested Citation

Hee-Kyung Kim (2008) Activity-based travel demand model with time-use and microsimulation incorporating intra-household interactions. Ph.D.. University of California, Irvine. Available at: https://uci.primo.exlibrisgroup.com/permalink/01CDL_IRV_INST/17uq3m8/alma991035093055004701 (Accessed: October 14, 2023).